[{"day":"01","department":[{"_id":"FrLo"}],"quality_controlled":"1","oa":1,"arxiv":1,"page":"8439-8457","publisher":"ML Research Press","date_created":"2023-08-21T09:27:43Z","status":"public","abstract":[{"lang":"eng","text":" We propose a stochastic conditional gradient method (CGM) for minimizing convex finite-sum objectives formed as a sum of smooth and non-smooth terms. Existing CGM variants for this template either suffer from slow convergence rates, or require carefully increasing the batch size over the course of the algorithm’s execution, which leads to computing full gradients. In contrast, the proposed method, equipped with a stochastic average gradient (SAG) estimator, requires only one sample per iteration. Nevertheless, it guarantees fast convergence rates on par with more sophisticated variance reduction techniques. In applications we put special emphasis on problems with a large number of separable constraints. Such problems are prevalent among semidefinite programming (SDP) formulations arising in machine learning and theoretical computer science. We provide numerical experiments on matrix completion, unsupervised clustering, and sparsest-cut SDPs. "}],"_id":"14093","publication_status":"published","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","external_id":{"arxiv":["2202.13212"]},"author":[{"full_name":"Dresdner, Gideon","last_name":"Dresdner","first_name":"Gideon"},{"full_name":"Vladarean, Maria-Luiza","first_name":"Maria-Luiza","last_name":"Vladarean"},{"full_name":"Rätsch, Gunnar","first_name":"Gunnar","last_name":"Rätsch"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","orcid":"0000-0002-4850-0683","last_name":"Locatello","first_name":"Francesco","full_name":"Locatello, Francesco"},{"full_name":"Cevher, Volkan","last_name":"Cevher","first_name":"Volkan"},{"full_name":"Yurtsever, Alp","last_name":"Yurtsever","first_name":"Alp"}],"publication_identifier":{"issn":["2640-3498"]},"volume":151,"title":" Faster one-sample stochastic conditional gradient method for composite convex minimization","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2202.13212"}],"intvolume":"       151","extern":"1","publication":"Proceedings of the 25th International Conference on Artificial Intelligence and Statistics","article_processing_charge":"No","language":[{"iso":"eng"}],"year":"2022","type":"conference","date_updated":"2023-09-06T10:28:17Z","citation":{"apa":"Dresdner, G., Vladarean, M.-L., Rätsch, G., Locatello, F., Cevher, V., &#38; Yurtsever, A. (2022).  Faster one-sample stochastic conditional gradient method for composite convex minimization. In <i>Proceedings of the 25th International Conference on Artificial Intelligence and Statistics</i> (Vol. 151, pp. 8439–8457). Virtual: ML Research Press.","short":"G. Dresdner, M.-L. Vladarean, G. Rätsch, F. Locatello, V. Cevher, A. Yurtsever, in:, Proceedings of the 25th International Conference on Artificial Intelligence and Statistics, ML Research Press, 2022, pp. 8439–8457.","ista":"Dresdner G, Vladarean M-L, Rätsch G, Locatello F, Cevher V, Yurtsever A. 2022.  Faster one-sample stochastic conditional gradient method for composite convex minimization. Proceedings of the 25th International Conference on Artificial Intelligence and Statistics. AISTATS: Conference on Artificial Intelligence and Statistics, PMLR, vol. 151, 8439–8457.","chicago":"Dresdner, Gideon, Maria-Luiza Vladarean, Gunnar Rätsch, Francesco Locatello, Volkan Cevher, and Alp Yurtsever. “ Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization.” In <i>Proceedings of the 25th International Conference on Artificial Intelligence and Statistics</i>, 151:8439–57. ML Research Press, 2022.","ama":"Dresdner G, Vladarean M-L, Rätsch G, Locatello F, Cevher V, Yurtsever A.  Faster one-sample stochastic conditional gradient method for composite convex minimization. In: <i>Proceedings of the 25th International Conference on Artificial Intelligence and Statistics</i>. Vol 151. ML Research Press; 2022:8439-8457.","ieee":"G. Dresdner, M.-L. Vladarean, G. Rätsch, F. Locatello, V. Cevher, and A. Yurtsever, “ Faster one-sample stochastic conditional gradient method for composite convex minimization,” in <i>Proceedings of the 25th International Conference on Artificial Intelligence and Statistics</i>, Virtual, 2022, vol. 151, pp. 8439–8457.","mla":"Dresdner, Gideon, et al. “ Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization.” <i>Proceedings of the 25th International Conference on Artificial Intelligence and Statistics</i>, vol. 151, ML Research Press, 2022, pp. 8439–57."},"month":"04","date_published":"2022-04-01T00:00:00Z","scopus_import":"1","conference":{"start_date":"2022-03-28","name":"AISTATS: Conference on Artificial Intelligence and Statistics","end_date":"2022-03-30","location":"Virtual"},"alternative_title":["PMLR"],"oa_version":"Preprint"},{"department":[{"_id":"FrLo"}],"day":"15","arxiv":1,"oa":1,"quality_controlled":"1","page":"16548-16562","publisher":"Neural Information Processing Systems Foundation","status":"public","date_created":"2023-08-21T12:12:42Z","_id":"14106","abstract":[{"text":"We show that deep networks trained to satisfy demographic parity often do so\r\nthrough a form of race or gender awareness, and that the more we force a network\r\nto be fair, the more accurately we can recover race or gender from the internal state\r\nof the network. Based on this observation, we investigate an alternative fairness\r\napproach: we add a second classification head to the network to explicitly predict\r\nthe protected attribute (such as race or gender) alongside the original task. After\r\ntraining the two-headed network, we enforce demographic parity by merging the\r\ntwo heads, creating a network with the same architecture as the original network.\r\nWe establish a close relationship between existing approaches and our approach\r\nby showing (1) that the decisions of a fair classifier are well-approximated by our\r\napproach, and (2) that an unfair and optimally accurate classifier can be recovered\r\nfrom a fair classifier and our second head predicting the protected attribute. We use\r\nour explicit formulation to argue that the existing fairness approaches, just as ours,\r\ndemonstrate disparate treatment and that they are likely to be unlawful in a wide\r\nrange of scenarios under US law.","lang":"eng"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication_status":"published","external_id":{"arxiv":["2204.04440"]},"author":[{"last_name":"Lohaus","first_name":"Michael","full_name":"Lohaus, Michael"},{"first_name":"Matthäus","last_name":"Kleindessner","full_name":"Kleindessner, Matthäus"},{"last_name":"Kenthapadi","first_name":"Krishnaram","full_name":"Kenthapadi, Krishnaram"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","last_name":"Locatello","orcid":"0000-0002-4850-0683","first_name":"Francesco","full_name":"Locatello, Francesco"},{"full_name":"Russell, Chris","last_name":"Russell","first_name":"Chris"}],"volume":35,"publication_identifier":{"isbn":["9781713871088"]},"intvolume":"        35","main_file_link":[{"url":"https://arxiv.org/abs/2204.04440","open_access":"1"}],"title":"Are two heads the same as one? Identifying disparate treatment in fair neural networks","article_processing_charge":"No","publication":"36th Conference on Neural Information Processing Systems","extern":"1","language":[{"iso":"eng"}],"year":"2022","date_updated":"2023-09-06T10:29:42Z","citation":{"ieee":"M. Lohaus, M. Kleindessner, K. Kenthapadi, F. Locatello, and C. Russell, “Are two heads the same as one? Identifying disparate treatment in fair neural networks,” in <i>36th Conference on Neural Information Processing Systems</i>, New Orleans, LA, United States, 2022, vol. 35, pp. 16548–16562.","mla":"Lohaus, Michael, et al. “Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks.” <i>36th Conference on Neural Information Processing Systems</i>, vol. 35, Neural Information Processing Systems Foundation, 2022, pp. 16548–62.","ama":"Lohaus M, Kleindessner M, Kenthapadi K, Locatello F, Russell C. Are two heads the same as one? Identifying disparate treatment in fair neural networks. In: <i>36th Conference on Neural Information Processing Systems</i>. Vol 35. Neural Information Processing Systems Foundation; 2022:16548-16562.","ista":"Lohaus M, Kleindessner M, Kenthapadi K, Locatello F, Russell C. 2022. Are two heads the same as one? Identifying disparate treatment in fair neural networks. 36th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 35, 16548–16562.","chicago":"Lohaus, Michael, Matthäus Kleindessner, Krishnaram Kenthapadi, Francesco Locatello, and Chris Russell. “Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks.” In <i>36th Conference on Neural Information Processing Systems</i>, 35:16548–62. Neural Information Processing Systems Foundation, 2022.","apa":"Lohaus, M., Kleindessner, M., Kenthapadi, K., Locatello, F., &#38; Russell, C. (2022). Are two heads the same as one? Identifying disparate treatment in fair neural networks. In <i>36th Conference on Neural Information Processing Systems</i> (Vol. 35, pp. 16548–16562). New Orleans, LA, United States: Neural Information Processing Systems Foundation.","short":"M. Lohaus, M. Kleindessner, K. Kenthapadi, F. Locatello, C. Russell, in:, 36th Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2022, pp. 16548–16562."},"type":"conference","scopus_import":"1","month":"12","date_published":"2022-12-15T00:00:00Z","alternative_title":["Advances in Neural Information Processing Systems"],"conference":{"end_date":"2022-12-09","start_date":"2022-11-28","name":"NeurIPS: Neural Information Processing Systems","location":"New Orleans, LA, United States"},"oa_version":"Preprint"},{"oa_version":"Preprint","external_id":{"arxiv":["2210.12733"]},"author":[{"full_name":"Yao, Jian","first_name":"Jian","last_name":"Yao"},{"full_name":"Hong, Yuxin","last_name":"Hong","first_name":"Yuxin"},{"first_name":"Chiyu","last_name":"Wang","full_name":"Wang, Chiyu"},{"first_name":"Tianjun","last_name":"Xiao","full_name":"Xiao, Tianjun"},{"full_name":"He, Tong","last_name":"He","first_name":"Tong"},{"full_name":"Locatello, Francesco","last_name":"Locatello","orcid":"0000-0002-4850-0683","first_name":"Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4"},{"last_name":"Wipf","first_name":"David","full_name":"Wipf, David"},{"last_name":"Fu","first_name":"Yanwei","full_name":"Fu, Yanwei"},{"full_name":"Zhang, Zheng","last_name":"Zhang","first_name":"Zheng"}],"conference":{"start_date":"2022-11-28","name":"NeurIPS: Neural Information Processing Systems","end_date":"2022-12-01","location":"New Orleans, LA, United States"},"doi":"10.48550/arXiv.2210.12733","date_published":"2022-10-23T00:00:00Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","month":"10","publication_status":"published","citation":{"ieee":"J. Yao <i>et al.</i>, “Self-supervised amodal video object segmentation,” in <i>36th Conference on Neural Information Processing Systems</i>, New Orleans, LA, United States, 2022.","mla":"Yao, Jian, et al. “Self-Supervised Amodal Video Object Segmentation.” <i>36th Conference on Neural Information Processing Systems</i>, 2022, doi:<a href=\"https://doi.org/10.48550/arXiv.2210.12733\">10.48550/arXiv.2210.12733</a>.","ama":"Yao J, Hong Y, Wang C, et al. Self-supervised amodal video object segmentation. In: <i>36th Conference on Neural Information Processing Systems</i>. ; 2022. doi:<a href=\"https://doi.org/10.48550/arXiv.2210.12733\">10.48550/arXiv.2210.12733</a>","ista":"Yao J, Hong Y, Wang C, Xiao T, He T, Locatello F, Wipf D, Fu Y, Zhang Z. 2022. Self-supervised amodal video object segmentation. 36th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems.","chicago":"Yao, Jian, Yuxin Hong, Chiyu Wang, Tianjun Xiao, Tong He, Francesco Locatello, David Wipf, Yanwei Fu, and Zheng Zhang. “Self-Supervised Amodal Video Object Segmentation.” In <i>36th Conference on Neural Information Processing Systems</i>, 2022. <a href=\"https://doi.org/10.48550/arXiv.2210.12733\">https://doi.org/10.48550/arXiv.2210.12733</a>.","apa":"Yao, J., Hong, Y., Wang, C., Xiao, T., He, T., Locatello, F., … Zhang, Z. (2022). Self-supervised amodal video object segmentation. In <i>36th Conference on Neural Information Processing Systems</i>. New Orleans, LA, United States. <a href=\"https://doi.org/10.48550/arXiv.2210.12733\">https://doi.org/10.48550/arXiv.2210.12733</a>","short":"J. Yao, Y. Hong, C. Wang, T. Xiao, T. He, F. Locatello, D. Wipf, Y. Fu, Z. Zhang, in:, 36th Conference on Neural Information Processing Systems, 2022."},"abstract":[{"lang":"eng","text":"Amodal perception requires inferring the full shape of an object that is partially occluded. This task is particularly challenging on two levels: (1) it requires more information than what is contained in the instant retina or imaging sensor, (2) it is difficult to obtain enough well-annotated amodal labels for supervision. To this end, this paper develops a new framework of\r\nSelf-supervised amodal Video object segmentation (SaVos). Our method efficiently leverages the visual information of video temporal sequences to infer the amodal mask of objects. The key intuition is that the occluded part of an object can be explained away if that part is visible in other frames, possibly deformed as long as the deformation can be reasonably learned.\r\nAccordingly, we derive a novel self-supervised learning paradigm that efficiently utilizes the visible object parts as the supervision to guide the training on videos. In addition to learning type prior to complete masks for known types, SaVos also learns the spatiotemporal prior, which is also useful for the amodal task and could generalize to unseen types. The proposed\r\nframework achieves the state-of-the-art performance on the synthetic amodal segmentation benchmark FISHBOWL and the real world benchmark KINS-Video-Car. Further, it lends itself well to being transferred to novel distributions using test-time adaptation, outperforming existing models even after the transfer to a new distribution."}],"date_updated":"2023-09-11T09:34:17Z","type":"conference","_id":"14107","status":"public","date_created":"2023-08-21T12:13:25Z","year":"2022","language":[{"iso":"eng"}],"extern":"1","article_processing_charge":"No","publication":"36th Conference on Neural Information Processing Systems","title":"Self-supervised amodal video object segmentation","main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2210.12733"}],"arxiv":1,"oa":1,"day":"23","department":[{"_id":"FrLo"}]},{"main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2203.04913"}],"title":"Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers","extern":"1","publication":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition","article_processing_charge":"No","year":"2022","language":[{"iso":"eng"}],"citation":{"mla":"Zietlow, Dominik, et al. “Leveling down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers.” <i>2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, Institute of Electrical and Electronics Engineers, 2022, pp. 10400–11, doi:<a href=\"https://doi.org/10.1109/cvpr52688.2022.01016\">10.1109/cvpr52688.2022.01016</a>.","ieee":"D. Zietlow <i>et al.</i>, “Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers,” in <i>2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, New Orleans, LA, United States, 2022, pp. 10400–10411.","ama":"Zietlow D, Lohaus M, Balakrishnan G, et al. Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers. In: <i>2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>. Institute of Electrical and Electronics Engineers; 2022:10400-10411. doi:<a href=\"https://doi.org/10.1109/cvpr52688.2022.01016\">10.1109/cvpr52688.2022.01016</a>","chicago":"Zietlow, Dominik, Michael Lohaus, Guha Balakrishnan, Matthaus Kleindessner, Francesco Locatello, Bernhard Scholkopf, and Chris Russell. “Leveling down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers.” In <i>2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i>, 10400–411. Institute of Electrical and Electronics Engineers, 2022. <a href=\"https://doi.org/10.1109/cvpr52688.2022.01016\">https://doi.org/10.1109/cvpr52688.2022.01016</a>.","ista":"Zietlow D, Lohaus M, Balakrishnan G, Kleindessner M, Locatello F, Scholkopf B, Russell C. 2022. Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR: Conference on Computer Vision and Pattern Recognition, 10400–10411.","short":"D. Zietlow, M. Lohaus, G. Balakrishnan, M. Kleindessner, F. Locatello, B. Scholkopf, C. Russell, in:, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Institute of Electrical and Electronics Engineers, 2022, pp. 10400–10411.","apa":"Zietlow, D., Lohaus, M., Balakrishnan, G., Kleindessner, M., Locatello, F., Scholkopf, B., &#38; Russell, C. (2022). Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers. In <i>2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition</i> (pp. 10400–10411). New Orleans, LA, United States: Institute of Electrical and Electronics Engineers. <a href=\"https://doi.org/10.1109/cvpr52688.2022.01016\">https://doi.org/10.1109/cvpr52688.2022.01016</a>"},"date_updated":"2023-09-11T09:19:14Z","type":"conference","date_published":"2022-07-01T00:00:00Z","month":"07","scopus_import":"1","conference":{"location":"New Orleans, LA, United States","name":"CVPR: Conference on Computer Vision and Pattern Recognition","start_date":"2022-06-18","end_date":"2022-06-24"},"doi":"10.1109/cvpr52688.2022.01016","oa_version":"Preprint","day":"01","department":[{"_id":"FrLo"}],"quality_controlled":"1","arxiv":1,"oa":1,"publisher":"Institute of Electrical and Electronics Engineers","page":"10400-10411","status":"public","date_created":"2023-08-21T12:18:00Z","abstract":[{"text":"Algorithmic fairness is frequently motivated in terms of a trade-off in which overall performance is decreased so as to improve performance on disadvantaged groups where the algorithm would otherwise be less accurate. Contrary to this, we find that applying existing fairness approaches to computer vision improve fairness by degrading the performance of classifiers across all groups (with increased degradation on the best performing groups). Extending the bias-variance decomposition for classification to fairness, we theoretically explain why the majority of fairness methods designed for low capacity models should not be used in settings involving high-capacity models, a scenario common to computer vision. We corroborate this analysis with extensive experimental support that shows that many of the fairness heuristics used in computer vision also degrade performance on the most disadvantaged groups. Building on these insights, we propose an adaptive augmentation strategy that, uniquely, of all methods tested, improves performance for the disadvantaged groups.","lang":"eng"}],"_id":"14114","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication_status":"published","author":[{"last_name":"Zietlow","first_name":"Dominik","full_name":"Zietlow, Dominik"},{"full_name":"Lohaus, Michael","last_name":"Lohaus","first_name":"Michael"},{"last_name":"Balakrishnan","first_name":"Guha","full_name":"Balakrishnan, Guha"},{"full_name":"Kleindessner, Matthaus","first_name":"Matthaus","last_name":"Kleindessner"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","first_name":"Francesco","last_name":"Locatello","orcid":"0000-0002-4850-0683","full_name":"Locatello, Francesco"},{"last_name":"Scholkopf","first_name":"Bernhard","full_name":"Scholkopf, Bernhard"},{"full_name":"Russell, Chris","last_name":"Russell","first_name":"Chris"}],"external_id":{"arxiv":["2203.04913"]},"publication_identifier":{"issn":["1063-6919"],"isbn":["9781665469470"],"eissn":["2575-7075"]}},{"department":[{"_id":"FrLo"}],"day":"14","oa":1,"arxiv":1,"title":"Neural attentive circuits","main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2210.08031"}],"intvolume":"        35","article_processing_charge":"No","publication":"36th Conference on Neural Information Processing Systems","extern":"1","language":[{"iso":"eng"}],"year":"2022","date_created":"2023-08-22T13:57:27Z","status":"public","_id":"14168","type":"conference","date_updated":"2023-09-11T09:29:09Z","citation":{"ama":"Rahaman N, Weiss M, Locatello F, et al. Neural attentive circuits. In: <i>36th Conference on Neural Information Processing Systems</i>. Vol 35. ; 2022.","mla":"Rahaman, Nasim, et al. “Neural Attentive Circuits.” <i>36th Conference on Neural Information Processing Systems</i>, vol. 35, 2022.","ieee":"N. Rahaman <i>et al.</i>, “Neural attentive circuits,” in <i>36th Conference on Neural Information Processing Systems</i>, New Orleans, United States, 2022, vol. 35.","short":"N. Rahaman, M. Weiss, F. Locatello, C. Pal, Y. Bengio, B. Schölkopf, L.E. Li, N. Ballas, in:, 36th Conference on Neural Information Processing Systems, 2022.","apa":"Rahaman, N., Weiss, M., Locatello, F., Pal, C., Bengio, Y., Schölkopf, B., … Ballas, N. (2022). Neural attentive circuits. In <i>36th Conference on Neural Information Processing Systems</i> (Vol. 35). New Orleans, United States.","chicago":"Rahaman, Nasim, Martin Weiss, Francesco Locatello, Chris Pal, Yoshua Bengio, Bernhard Schölkopf, Li Erran Li, and Nicolas Ballas. “Neural Attentive Circuits.” In <i>36th Conference on Neural Information Processing Systems</i>, Vol. 35, 2022.","ista":"Rahaman N, Weiss M, Locatello F, Pal C, Bengio Y, Schölkopf B, Li LE, Ballas N. 2022. Neural attentive circuits. 36th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems,  Advances in Neural Information Processing Systems, vol. 35."},"abstract":[{"lang":"eng","text":"Recent work has seen the development of general purpose neural architectures\r\nthat can be trained to perform tasks across diverse data modalities. General\r\npurpose models typically make few assumptions about the underlying\r\ndata-structure and are known to perform well in the large-data regime. At the\r\nsame time, there has been growing interest in modular neural architectures that\r\nrepresent the data using sparsely interacting modules. These models can be more\r\nrobust out-of-distribution, computationally efficient, and capable of\r\nsample-efficient adaptation to new data. However, they tend to make\r\ndomain-specific assumptions about the data, and present challenges in how\r\nmodule behavior (i.e., parameterization) and connectivity (i.e., their layout)\r\ncan be jointly learned. In this work, we introduce a general purpose, yet\r\nmodular neural architecture called Neural Attentive Circuits (NACs) that\r\njointly learns the parameterization and a sparse connectivity of neural modules\r\nwithout using domain knowledge. NACs are best understood as the combination of\r\ntwo systems that are jointly trained end-to-end: one that determines the module\r\nconfiguration and the other that executes it on an input. We demonstrate\r\nqualitatively that NACs learn diverse and meaningful module configurations on\r\nthe NLVR2 dataset without additional supervision. Quantitatively, we show that\r\nby incorporating modularity in this way, NACs improve upon a strong non-modular\r\nbaseline in terms of low-shot adaptation on CIFAR and CUBs dataset by about\r\n10%, and OOD robustness on Tiny ImageNet-R by about 2.5%. Further, we find that\r\nNACs can achieve an 8x speedup at inference time while losing less than 3%\r\nperformance. Finally, we find NACs to yield competitive results on diverse data\r\nmodalities spanning point-cloud classification, symbolic processing and\r\ntext-classification from ASCII bytes, thereby confirming its general purpose\r\nnature."}],"publication_status":"published","month":"10","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_published":"2022-10-14T00:00:00Z","conference":{"name":"NeurIPS: Neural Information Processing Systems","start_date":"2022-11-29","end_date":"2022-12-01","location":"New Orleans, United States"},"alternative_title":[" Advances in Neural Information Processing Systems"],"external_id":{"arxiv":["2210.08031"]},"author":[{"last_name":"Rahaman","first_name":"Nasim","full_name":"Rahaman, Nasim"},{"last_name":"Weiss","first_name":"Martin","full_name":"Weiss, Martin"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","last_name":"Locatello","orcid":"0000-0002-4850-0683","first_name":"Francesco","full_name":"Locatello, Francesco"},{"last_name":"Pal","first_name":"Chris","full_name":"Pal, Chris"},{"full_name":"Bengio, Yoshua","last_name":"Bengio","first_name":"Yoshua"},{"first_name":"Bernhard","last_name":"Schölkopf","full_name":"Schölkopf, Bernhard"},{"last_name":"Li","first_name":"Li Erran","full_name":"Li, Li Erran"},{"full_name":"Ballas, Nicolas","last_name":"Ballas","first_name":"Nicolas"}],"volume":35,"oa_version":"Preprint"},{"oa_version":"Preprint","conference":{"location":"Baltimore, MD, United States","start_date":"2022-07-17","name":"International Conference on Machine Learning","end_date":"2022-07-23"},"alternative_title":["PMLR"],"month":"07","date_published":"2022-07-22T00:00:00Z","type":"conference","date_updated":"2023-09-11T10:08:14Z","citation":{"ieee":"A. Dittadi, S. Papa, M. D. Vita, B. Schölkopf, O. Winther, and F. Locatello, “Generalization and robustness implications in object-centric learning,” in <i>Proceedings of the 39th International Conference on Machine Learning</i>, Baltimore, MD, United States, vol. 2022, pp. 5221–5285.","mla":"Dittadi, Andrea, et al. “Generalization and Robustness Implications in Object-Centric Learning.” <i>Proceedings of the 39th International Conference on Machine Learning</i>, vol. 2022, ML Research Press, pp. 5221–85.","ama":"Dittadi A, Papa S, Vita MD, Schölkopf B, Winther O, Locatello F. Generalization and robustness implications in object-centric learning. In: <i>Proceedings of the 39th International Conference on Machine Learning</i>. Vol 2022. ML Research Press; :5221-5285.","ista":"Dittadi A, Papa S, Vita MD, Schölkopf B, Winther O, Locatello F. Generalization and robustness implications in object-centric learning. Proceedings of the 39th International Conference on Machine Learning. International Conference on Machine Learning, PMLR, vol. 2022, 5221–5285.","chicago":"Dittadi, Andrea, Samuele Papa, Michele De Vita, Bernhard Schölkopf, Ole Winther, and Francesco Locatello. “Generalization and Robustness Implications in Object-Centric Learning.” In <i>Proceedings of the 39th International Conference on Machine Learning</i>, 2022:5221–85. ML Research Press, n.d.","apa":"Dittadi, A., Papa, S., Vita, M. D., Schölkopf, B., Winther, O., &#38; Locatello, F. (n.d.). Generalization and robustness implications in object-centric learning. In <i>Proceedings of the 39th International Conference on Machine Learning</i> (Vol. 2022, pp. 5221–5285). Baltimore, MD, United States: ML Research Press.","short":"A. Dittadi, S. Papa, M.D. Vita, B. Schölkopf, O. Winther, F. Locatello, in:, Proceedings of the 39th International Conference on Machine Learning, ML Research Press, n.d., pp. 5221–5285."},"year":"2022","language":[{"iso":"eng"}],"extern":"1","article_processing_charge":"No","publication":"Proceedings of the 39th International Conference on Machine Learning","title":"Generalization and robustness implications in object-centric learning","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2107.00637"}],"intvolume":"      2022","volume":2022,"author":[{"first_name":"Andrea","last_name":"Dittadi","full_name":"Dittadi, Andrea"},{"last_name":"Papa","first_name":"Samuele","full_name":"Papa, Samuele"},{"last_name":"Vita","first_name":"Michele De","full_name":"Vita, Michele De"},{"first_name":"Bernhard","last_name":"Schölkopf","full_name":"Schölkopf, Bernhard"},{"last_name":"Winther","first_name":"Ole","full_name":"Winther, Ole"},{"full_name":"Locatello, Francesco","orcid":"0000-0002-4850-0683","last_name":"Locatello","first_name":"Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4"}],"external_id":{"arxiv":["2107.00637"]},"publication_status":"submitted","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","abstract":[{"lang":"eng","text":"The idea behind object-centric representation learning is that natural scenes can better be modeled as compositions of objects and their relations as opposed to distributed representations. This inductive bias can be injected into neural networks to potentially improve systematic generalization and performance of downstream tasks in scenes with multiple objects. In this paper, we train state-of-the-art unsupervised models on five common multi-object datasets and evaluate segmentation metrics and downstream object property prediction. In addition, we study generalization and robustness by investigating the settings where either a single object is out of distribution -- e.g., having an unseen color, texture, or shape -- or global properties of the scene are altered -- e.g., by occlusions, cropping, or increasing the number of objects. From our experimental study, we find object-centric representations to be useful for\r\ndownstream tasks and generally robust to most distribution shifts affecting objects. However, when the distribution shift affects the input in a less structured manner, robustness in terms of segmentation and downstream task performance may vary significantly across models and distribution shifts. "}],"_id":"14170","date_created":"2023-08-22T13:59:55Z","status":"public","page":"5221-5285","publisher":"ML Research Press","quality_controlled":"1","oa":1,"arxiv":1,"day":"22","department":[{"_id":"FrLo"}]},{"type":"conference","citation":{"ama":"Rolland P, Cevher V, Kleindessner M, et al. Score matching enables causal discovery of nonlinear additive noise  models. In: <i>Proceedings of the 39th International Conference on Machine Learning</i>. Vol 162. ML Research Press; 2022:18741-18753.","ieee":"P. Rolland <i>et al.</i>, “Score matching enables causal discovery of nonlinear additive noise  models,” in <i>Proceedings of the 39th International Conference on Machine Learning</i>, Baltimore, MD, United States, 2022, vol. 162, pp. 18741–18753.","mla":"Rolland, Paul, et al. “Score Matching Enables Causal Discovery of Nonlinear Additive Noise  Models.” <i>Proceedings of the 39th International Conference on Machine Learning</i>, vol. 162, ML Research Press, 2022, pp. 18741–53.","apa":"Rolland, P., Cevher, V., Kleindessner, M., Russel, C., Schölkopf, B., Janzing, D., &#38; Locatello, F. (2022). Score matching enables causal discovery of nonlinear additive noise  models. In <i>Proceedings of the 39th International Conference on Machine Learning</i> (Vol. 162, pp. 18741–18753). Baltimore, MD, United States: ML Research Press.","short":"P. Rolland, V. Cevher, M. Kleindessner, C. Russel, B. Schölkopf, D. Janzing, F. Locatello, in:, Proceedings of the 39th International Conference on Machine Learning, ML Research Press, 2022, pp. 18741–18753.","ista":"Rolland P, Cevher V, Kleindessner M, Russel C, Schölkopf B, Janzing D, Locatello F. 2022. Score matching enables causal discovery of nonlinear additive noise  models. Proceedings of the 39th International Conference on Machine Learning. International Conference on Machine Learning, PMLR, vol. 162, 18741–18753.","chicago":"Rolland, Paul, Volkan Cevher, Matthäus Kleindessner, Chris Russel, Bernhard Schölkopf, Dominik Janzing, and Francesco Locatello. “Score Matching Enables Causal Discovery of Nonlinear Additive Noise  Models.” In <i>Proceedings of the 39th International Conference on Machine Learning</i>, 162:18741–53. ML Research Press, 2022."},"date_updated":"2023-09-11T10:14:20Z","date_published":"2022-07-22T00:00:00Z","month":"07","conference":{"location":"Baltimore, MD, United States","end_date":"2022-07-23","name":"International Conference on Machine Learning","start_date":"2022-07-17"},"alternative_title":["PMLR"],"oa_version":"Preprint","main_file_link":[{"url":"https://arxiv.org/abs/2203.04413","open_access":"1"}],"title":"Score matching enables causal discovery of nonlinear additive noise  models","intvolume":"       162","extern":"1","article_processing_charge":"No","publication":"Proceedings of the 39th International Conference on Machine Learning","language":[{"iso":"eng"}],"year":"2022","abstract":[{"text":"This paper demonstrates how to recover causal graphs from the score of the\r\ndata distribution in non-linear additive (Gaussian) noise models. Using score\r\nmatching algorithms as a building block, we show how to design a new generation\r\nof scalable causal discovery methods. To showcase our approach, we also propose\r\na new efficient method for approximating the score's Jacobian, enabling to\r\nrecover the causal graph. Empirically, we find that the new algorithm, called\r\nSCORE, is competitive with state-of-the-art causal discovery methods while\r\nbeing significantly faster.","lang":"eng"}],"_id":"14171","publication_status":"published","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","external_id":{"arxiv":["2203.04413"]},"author":[{"first_name":"Paul","last_name":"Rolland","full_name":"Rolland, Paul"},{"first_name":"Volkan","last_name":"Cevher","full_name":"Cevher, Volkan"},{"first_name":"Matthäus","last_name":"Kleindessner","full_name":"Kleindessner, Matthäus"},{"full_name":"Russel, Chris","first_name":"Chris","last_name":"Russel"},{"last_name":"Schölkopf","first_name":"Bernhard","full_name":"Schölkopf, Bernhard"},{"full_name":"Janzing, Dominik","first_name":"Dominik","last_name":"Janzing"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","orcid":"0000-0002-4850-0683","last_name":"Locatello","first_name":"Francesco","full_name":"Locatello, Francesco"}],"volume":162,"day":"22","department":[{"_id":"FrLo"}],"quality_controlled":"1","oa":1,"arxiv":1,"page":"18741-18753","publisher":"ML Research Press","date_created":"2023-08-22T14:00:18Z","status":"public"},{"year":"2022","language":[{"iso":"eng"}],"date_created":"2023-08-22T14:00:50Z","status":"public","article_processing_charge":"No","publication":"10th International Conference on Learning Representations","extern":"1","oa":1,"arxiv":1,"title":"Visual representation learning does not generalize strongly within the  same domain","quality_controlled":"1","main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2107.08221"}],"department":[{"_id":"FrLo"}],"day":"25","oa_version":"Preprint","conference":{"location":"Virtual","name":"ICLR: International Conference on Learning Representations","start_date":"2022-04-25","end_date":"2022-04-29"},"external_id":{"arxiv":["2107.08221"]},"author":[{"last_name":"Schott","first_name":"Lukas","full_name":"Schott, Lukas"},{"last_name":"Kügelgen","first_name":"Julius von","full_name":"Kügelgen, Julius von"},{"full_name":"Träuble, Frederik","first_name":"Frederik","last_name":"Träuble"},{"last_name":"Gehler","first_name":"Peter","full_name":"Gehler, Peter"},{"full_name":"Russell, Chris","first_name":"Chris","last_name":"Russell"},{"last_name":"Bethge","first_name":"Matthias","full_name":"Bethge, Matthias"},{"full_name":"Schölkopf, Bernhard","last_name":"Schölkopf","first_name":"Bernhard"},{"full_name":"Locatello, Francesco","last_name":"Locatello","orcid":"0000-0002-4850-0683","first_name":"Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4"},{"last_name":"Brendel","first_name":"Wieland","full_name":"Brendel, Wieland"}],"publication_status":"published","month":"04","date_published":"2022-04-25T00:00:00Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","_id":"14172","type":"conference","citation":{"ama":"Schott L, Kügelgen J von, Träuble F, et al. Visual representation learning does not generalize strongly within the  same domain. In: <i>10th International Conference on Learning Representations</i>. ; 2022.","mla":"Schott, Lukas, et al. “Visual Representation Learning Does Not Generalize Strongly within the  Same Domain.” <i>10th International Conference on Learning Representations</i>, 2022.","ieee":"L. Schott <i>et al.</i>, “Visual representation learning does not generalize strongly within the  same domain,” in <i>10th International Conference on Learning Representations</i>, Virtual, 2022.","short":"L. Schott, J. von Kügelgen, F. Träuble, P. Gehler, C. Russell, M. Bethge, B. Schölkopf, F. Locatello, W. Brendel, in:, 10th International Conference on Learning Representations, 2022.","apa":"Schott, L., Kügelgen, J. von, Träuble, F., Gehler, P., Russell, C., Bethge, M., … Brendel, W. (2022). Visual representation learning does not generalize strongly within the  same domain. In <i>10th International Conference on Learning Representations</i>. Virtual.","chicago":"Schott, Lukas, Julius von Kügelgen, Frederik Träuble, Peter Gehler, Chris Russell, Matthias Bethge, Bernhard Schölkopf, Francesco Locatello, and Wieland Brendel. “Visual Representation Learning Does Not Generalize Strongly within the  Same Domain.” In <i>10th International Conference on Learning Representations</i>, 2022.","ista":"Schott L, Kügelgen J von, Träuble F, Gehler P, Russell C, Bethge M, Schölkopf B, Locatello F, Brendel W. 2022. Visual representation learning does not generalize strongly within the  same domain. 10th International Conference on Learning Representations. ICLR: International Conference on Learning Representations."},"abstract":[{"text":"An important component for generalization in machine learning is to uncover underlying latent factors of variation as well as the mechanism through which each factor acts in the world. In this paper, we test whether 17 unsupervised, weakly supervised, and fully supervised representation learning approaches correctly infer the generative factors of variation in simple datasets (dSprites, Shapes3D, MPI3D) from controlled environments, and on our contributed CelebGlow dataset. In contrast to prior robustness work that introduces novel factors of variation during test time, such as blur or other (un)structured noise, we here recompose, interpolate, or extrapolate only existing factors of variation from the training data set (e.g., small and medium-sized objects during training and large objects during testing). Models\r\nthat learn the correct mechanism should be able to generalize to this benchmark. In total, we train and test 2000+ models and observe that all of them struggle to learn the underlying mechanism regardless of supervision signal and architectural bias. Moreover, the generalization capabilities of all tested models drop significantly as we move from artificial datasets towards\r\nmore realistic real-world datasets. Despite their inability to identify the correct mechanism, the models are quite modular as their ability to infer other in-distribution factors remains fairly stable, providing only a single factoris out-of-distribution. These results point to an important yet understudied problem of learning mechanistic models of observations that can facilitate\r\ngeneralization.","lang":"eng"}],"date_updated":"2023-09-11T09:40:52Z"},{"oa_version":"Preprint","conference":{"location":"New Orleans, LA, United States","name":"NeurIPS: Neural Information Processing Systems","start_date":"2022-11-28","end_date":"2022-12-09"},"alternative_title":["Advances in Neural Information Processing Systems"],"date_published":"2022-12-15T00:00:00Z","month":"12","scopus_import":"1","type":"conference","date_updated":"2023-09-06T10:34:43Z","citation":{"ista":"Wenzel F, Dittadi A, Gehler PV, Carl-Johann Simon-Gabriel C-JS-G, Horn M, Zietlow D, Kernert D, Russell C, Brox T, Schiele B, Schölkopf B, Locatello F. 2022. Assaying out-of-distribution generalization in transfer learning. 36th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 35, 7181–7198.","chicago":"Wenzel, Florian, Andrea Dittadi, Peter Vincent Gehler, Carl-Johann Simon-Gabriel Carl-Johann Simon-Gabriel, Max Horn, Dominik Zietlow, David Kernert, et al. “Assaying Out-of-Distribution Generalization in Transfer Learning.” In <i>36th Conference on Neural Information Processing Systems</i>, 35:7181–98. Neural Information Processing Systems Foundation, 2022.","apa":"Wenzel, F., Dittadi, A., Gehler, P. V., Carl-Johann Simon-Gabriel, C.-J. S.-G., Horn, M., Zietlow, D., … Locatello, F. (2022). Assaying out-of-distribution generalization in transfer learning. In <i>36th Conference on Neural Information Processing Systems</i> (Vol. 35, pp. 7181–7198). New Orleans, LA, United States: Neural Information Processing Systems Foundation.","short":"F. Wenzel, A. Dittadi, P.V. Gehler, C.-J.S.-G. Carl-Johann Simon-Gabriel, M. Horn, D. Zietlow, D. Kernert, C. Russell, T. Brox, B. Schiele, B. Schölkopf, F. Locatello, in:, 36th Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, 2022, pp. 7181–7198.","ieee":"F. Wenzel <i>et al.</i>, “Assaying out-of-distribution generalization in transfer learning,” in <i>36th Conference on Neural Information Processing Systems</i>, New Orleans, LA, United States, 2022, vol. 35, pp. 7181–7198.","mla":"Wenzel, Florian, et al. “Assaying Out-of-Distribution Generalization in Transfer Learning.” <i>36th Conference on Neural Information Processing Systems</i>, vol. 35, Neural Information Processing Systems Foundation, 2022, pp. 7181–98.","ama":"Wenzel F, Dittadi A, Gehler PV, et al. Assaying out-of-distribution generalization in transfer learning. In: <i>36th Conference on Neural Information Processing Systems</i>. Vol 35. Neural Information Processing Systems Foundation; 2022:7181-7198."},"language":[{"iso":"eng"}],"year":"2022","extern":"1","publication":"36th Conference on Neural Information Processing Systems","article_processing_charge":"No","title":"Assaying out-of-distribution generalization in transfer learning","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2207.09239"}],"intvolume":"        35","publication_identifier":{"isbn":["9781713871088"]},"volume":35,"external_id":{"arxiv":["2207.09239"]},"author":[{"full_name":"Wenzel, Florian","first_name":"Florian","last_name":"Wenzel"},{"full_name":"Dittadi, Andrea","last_name":"Dittadi","first_name":"Andrea"},{"full_name":"Gehler, Peter Vincent","first_name":"Peter Vincent","last_name":"Gehler"},{"full_name":"Carl-Johann Simon-Gabriel, Carl-Johann Simon-Gabriel","first_name":"Carl-Johann Simon-Gabriel","last_name":"Carl-Johann Simon-Gabriel"},{"full_name":"Horn, Max","last_name":"Horn","first_name":"Max"},{"first_name":"Dominik","last_name":"Zietlow","full_name":"Zietlow, Dominik"},{"full_name":"Kernert, David","last_name":"Kernert","first_name":"David"},{"first_name":"Chris","last_name":"Russell","full_name":"Russell, Chris"},{"first_name":"Thomas","last_name":"Brox","full_name":"Brox, Thomas"},{"first_name":"Bernt","last_name":"Schiele","full_name":"Schiele, Bernt"},{"first_name":"Bernhard","last_name":"Schölkopf","full_name":"Schölkopf, Bernhard"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","orcid":"0000-0002-4850-0683","last_name":"Locatello","first_name":"Francesco","full_name":"Locatello, Francesco"}],"publication_status":"published","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","abstract":[{"text":"Since out-of-distribution generalization is a generally ill-posed problem, various proxy targets (e.g., calibration, adversarial robustness, algorithmic corruptions, invariance across shifts) were studied across different research programs resulting in different recommendations. While sharing the same aspirational goal, these approaches have never been tested under the same\r\nexperimental conditions on real data. In this paper, we take a unified view of previous work, highlighting message discrepancies that we address empirically, and providing recommendations on how to measure the robustness of a model and how to improve it. To this end, we collect 172 publicly available dataset pairs for training and out-of-distribution evaluation of accuracy, calibration error, adversarial attacks, environment invariance, and synthetic corruptions. We fine-tune over 31k networks, from nine different architectures in the many- and\r\nfew-shot setting. Our findings confirm that in- and out-of-distribution accuracies tend to increase jointly, but show that their relation is largely dataset-dependent, and in general more nuanced and more complex than posited by previous, smaller scale studies.","lang":"eng"}],"_id":"14173","date_created":"2023-08-22T14:01:13Z","status":"public","publisher":"Neural Information Processing Systems Foundation","page":"7181-7198","quality_controlled":"1","oa":1,"arxiv":1,"day":"15","department":[{"_id":"FrLo"}]},{"oa_version":"Preprint","conference":{"location":"Virtual","end_date":"2022-04-29","start_date":"2022-04-25","name":"ICLR: International Conference on Learning Representations"},"external_id":{"arxiv":["2107.05686"]},"author":[{"first_name":"Andrea","last_name":"Dittadi","full_name":"Dittadi, Andrea"},{"first_name":"Frederik","last_name":"Träuble","full_name":"Träuble, Frederik"},{"full_name":"Wüthrich, Manuel","first_name":"Manuel","last_name":"Wüthrich"},{"last_name":"Widmaier","first_name":"Felix","full_name":"Widmaier, Felix"},{"first_name":"Peter","last_name":"Gehler","full_name":"Gehler, Peter"},{"full_name":"Winther, Ole","first_name":"Ole","last_name":"Winther"},{"full_name":"Locatello, Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","first_name":"Francesco","orcid":"0000-0002-4850-0683","last_name":"Locatello"},{"full_name":"Bachem, Olivier","first_name":"Olivier","last_name":"Bachem"},{"full_name":"Schölkopf, Bernhard","first_name":"Bernhard","last_name":"Schölkopf"},{"first_name":"Stefan","last_name":"Bauer","full_name":"Bauer, Stefan"}],"publication_status":"published","date_published":"2022-04-25T00:00:00Z","month":"04","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","_id":"14174","type":"conference","abstract":[{"lang":"eng","text":"Building sample-efficient agents that generalize out-of-distribution (OOD) in real-world settings remains a fundamental unsolved problem on the path towards achieving higher-level cognition. One particularly promising approach is to begin with low-dimensional, pretrained representations of our world, which should facilitate efficient downstream learning and generalization. By training 240 representations and over 10,000 reinforcement learning (RL) policies on a simulated robotic setup, we evaluate to what extent different properties of\r\npretrained VAE-based representations affect the OOD generalization of downstream agents. We observe that many agents are surprisingly robust to realistic distribution shifts, including the challenging sim-to-real case. In addition, we find that the generalization performance of a simple downstream proxy task reliably predicts the generalization performance of our RL agents\r\nunder a wide range of OOD settings. Such proxy tasks can thus be used to select pretrained representations that will lead to agents that generalize."}],"date_updated":"2023-09-11T09:48:36Z","citation":{"short":"A. Dittadi, F. Träuble, M. Wüthrich, F. Widmaier, P. Gehler, O. Winther, F. Locatello, O. Bachem, B. Schölkopf, S. Bauer, in:, 10th International Conference on Learning Representations, 2022.","apa":"Dittadi, A., Träuble, F., Wüthrich, M., Widmaier, F., Gehler, P., Winther, O., … Bauer, S. (2022). The role of pretrained representations for the OOD generalization of  reinforcement learning agents. In <i>10th International Conference on Learning Representations</i>. Virtual.","chicago":"Dittadi, Andrea, Frederik Träuble, Manuel Wüthrich, Felix Widmaier, Peter Gehler, Ole Winther, Francesco Locatello, Olivier Bachem, Bernhard Schölkopf, and Stefan Bauer. “The Role of Pretrained Representations for the OOD Generalization of  Reinforcement Learning Agents.” In <i>10th International Conference on Learning Representations</i>, 2022.","ista":"Dittadi A, Träuble F, Wüthrich M, Widmaier F, Gehler P, Winther O, Locatello F, Bachem O, Schölkopf B, Bauer S. 2022. The role of pretrained representations for the OOD generalization of  reinforcement learning agents. 10th International Conference on Learning Representations. ICLR: International Conference on Learning Representations.","ama":"Dittadi A, Träuble F, Wüthrich M, et al. The role of pretrained representations for the OOD generalization of  reinforcement learning agents. In: <i>10th International Conference on Learning Representations</i>. ; 2022.","mla":"Dittadi, Andrea, et al. “The Role of Pretrained Representations for the OOD Generalization of  Reinforcement Learning Agents.” <i>10th International Conference on Learning Representations</i>, 2022.","ieee":"A. Dittadi <i>et al.</i>, “The role of pretrained representations for the OOD generalization of  reinforcement learning agents,” in <i>10th International Conference on Learning Representations</i>, Virtual, 2022."},"year":"2022","language":[{"iso":"eng"}],"date_created":"2023-08-22T14:02:13Z","status":"public","article_processing_charge":"No","publication":"10th International Conference on Learning Representations","extern":"1","oa":1,"arxiv":1,"quality_controlled":"1","main_file_link":[{"url":" https://doi.org/10.48550/arXiv.2107.05686","open_access":"1"}],"title":"The role of pretrained representations for the OOD generalization of  reinforcement learning agents","department":[{"_id":"FrLo"}],"day":"25"},{"language":[{"iso":"eng"}],"year":"2022","date_created":"2023-08-22T14:02:34Z","status":"public","publication":"10th International Conference on Learning Representations","article_processing_charge":"No","extern":"1","oa":1,"arxiv":1,"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2110.05304","open_access":"1"}],"quality_controlled":"1","title":"You mostly walk alone: Analyzing feature attribution in trajectory prediction","department":[{"_id":"FrLo"}],"day":"25","oa_version":"Preprint","conference":{"start_date":"2022-04-25","name":"ICLR: International Conference on Learning Representations","end_date":"2022-04-29","location":"Virtual"},"author":[{"full_name":"Makansi, Osama","last_name":"Makansi","first_name":"Osama"},{"full_name":"Kügelgen, Julius von","last_name":"Kügelgen","first_name":"Julius von"},{"full_name":"Locatello, Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","last_name":"Locatello","orcid":"0000-0002-4850-0683","first_name":"Francesco"},{"last_name":"Gehler","first_name":"Peter","full_name":"Gehler, Peter"},{"first_name":"Dominik","last_name":"Janzing","full_name":"Janzing, Dominik"},{"full_name":"Brox, Thomas","first_name":"Thomas","last_name":"Brox"},{"full_name":"Schölkopf, Bernhard","first_name":"Bernhard","last_name":"Schölkopf"}],"external_id":{"arxiv":["2110.05304"]},"publication_status":"published","month":"04","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_published":"2022-04-25T00:00:00Z","_id":"14175","type":"conference","abstract":[{"text":"Predicting the future trajectory of a moving agent can be easy when the past trajectory continues smoothly but is challenging when complex interactions with other agents are involved. Recent deep learning approaches for trajectory prediction show promising performance and partially attribute this to successful reasoning about agent-agent interactions. However, it remains unclear which features such black-box models actually learn to use for making predictions. This paper proposes a procedure that quantifies the contributions\r\nof different cues to model performance based on a variant of Shapley values. Applying this procedure to state-of-the-art trajectory prediction methods on standard benchmark datasets shows that they are, in fact, unable to reason about interactions. Instead, the past trajectory of the target is the only feature used for predicting its future. For a task with richer social\r\ninteraction patterns, on the other hand, the tested models do pick up such interactions to a certain extent, as quantified by our feature attribution method. We discuss the limits of the proposed method and its links to causality.","lang":"eng"}],"date_updated":"2023-09-11T09:52:20Z","citation":{"mla":"Makansi, Osama, et al. “You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction.” <i>10th International Conference on Learning Representations</i>, 2022.","ieee":"O. Makansi <i>et al.</i>, “You mostly walk alone: Analyzing feature attribution in trajectory prediction,” in <i>10th International Conference on Learning Representations</i>, Virtual, 2022.","ama":"Makansi O, Kügelgen J von, Locatello F, et al. You mostly walk alone: Analyzing feature attribution in trajectory prediction. In: <i>10th International Conference on Learning Representations</i>. ; 2022.","chicago":"Makansi, Osama, Julius von Kügelgen, Francesco Locatello, Peter Gehler, Dominik Janzing, Thomas Brox, and Bernhard Schölkopf. “You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction.” In <i>10th International Conference on Learning Representations</i>, 2022.","ista":"Makansi O, Kügelgen J von, Locatello F, Gehler P, Janzing D, Brox T, Schölkopf B. 2022. You mostly walk alone: Analyzing feature attribution in trajectory prediction. 10th International Conference on Learning Representations. ICLR: International Conference on Learning Representations.","short":"O. Makansi, J. von Kügelgen, F. Locatello, P. Gehler, D. Janzing, T. Brox, B. Schölkopf, in:, 10th International Conference on Learning Representations, 2022.","apa":"Makansi, O., Kügelgen, J. von, Locatello, F., Gehler, P., Janzing, D., Brox, T., &#38; Schölkopf, B. (2022). You mostly walk alone: Analyzing feature attribution in trajectory prediction. In <i>10th International Conference on Learning Representations</i>. Virtual."}},{"day":"04","department":[{"_id":"FrLo"}],"main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2211.02348"}],"quality_controlled":"1","title":"A general purpose neural architecture for geospatial systems","oa":1,"arxiv":1,"extern":"1","article_processing_charge":"No","publication":"36th Conference on Neural Information Processing Systems","date_created":"2023-08-22T14:21:47Z","status":"public","language":[{"iso":"eng"}],"year":"2022","type":"conference","abstract":[{"text":"Geospatial Information Systems are used by researchers and Humanitarian Assistance and Disaster Response (HADR) practitioners to support a wide variety of important applications. However, collaboration between these actors is difficult due to the heterogeneous nature of geospatial data modalities (e.g., multi-spectral images of various resolutions, timeseries, weather data) and diversity of tasks (e.g., regression of human activity indicators or detecting forest fires). In this work, we present a roadmap towards the construction of a general-purpose neural architecture (GPNA) with a geospatial inductive bias, pre-trained on large amounts of unlabelled earth observation data in a self-supervised manner. We envision how such a model may facilitate cooperation between members of the community. We show preliminary results on the first step of the roadmap, where we instantiate an architecture that can process a wide variety of geospatial data modalities and demonstrate that it can achieve competitive performance with domain-specific architectures on tasks relating to the U.N.'s Sustainable Development Goals.","lang":"eng"}],"citation":{"chicago":"Rahaman, Nasim, Martin Weiss, Frederik Träuble, Francesco Locatello, Alexandre Lacoste, Yoshua Bengio, Chris Pal, Li Erran Li, and Bernhard Schölkopf. “A General Purpose Neural Architecture for Geospatial Systems.” In <i>36th Conference on Neural Information Processing Systems</i>, n.d.","ista":"Rahaman N, Weiss M, Träuble F, Locatello F, Lacoste A, Bengio Y, Pal C, Li LE, Schölkopf B. A general purpose neural architecture for geospatial systems. 36th Conference on Neural Information Processing Systems. NeurIPS: Neural Information Processing Systems.","short":"N. Rahaman, M. Weiss, F. Träuble, F. Locatello, A. Lacoste, Y. Bengio, C. Pal, L.E. Li, B. Schölkopf, in:, 36th Conference on Neural Information Processing Systems, n.d.","apa":"Rahaman, N., Weiss, M., Träuble, F., Locatello, F., Lacoste, A., Bengio, Y., … Schölkopf, B. (n.d.). A general purpose neural architecture for geospatial systems. In <i>36th Conference on Neural Information Processing Systems</i>. New Orleans, LA, United States.","mla":"Rahaman, Nasim, et al. “A General Purpose Neural Architecture for Geospatial Systems.” <i>36th Conference on Neural Information Processing Systems</i>.","ieee":"N. Rahaman <i>et al.</i>, “A general purpose neural architecture for geospatial systems,” in <i>36th Conference on Neural Information Processing Systems</i>, New Orleans, LA, United States.","ama":"Rahaman N, Weiss M, Träuble F, et al. A general purpose neural architecture for geospatial systems. In: <i>36th Conference on Neural Information Processing Systems</i>."},"date_updated":"2023-09-13T09:35:59Z","_id":"14215","publication_status":"submitted","month":"11","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_published":"2022-11-04T00:00:00Z","conference":{"name":"NeurIPS: Neural Information Processing Systems","start_date":"2022-11-28","end_date":"2022-12-09","location":"New Orleans, LA, United States"},"external_id":{"arxiv":["2211.02348"]},"author":[{"last_name":"Rahaman","first_name":"Nasim","full_name":"Rahaman, Nasim"},{"last_name":"Weiss","first_name":"Martin","full_name":"Weiss, Martin"},{"first_name":"Frederik","last_name":"Träuble","full_name":"Träuble, Frederik"},{"first_name":"Francesco","last_name":"Locatello","orcid":"0000-0002-4850-0683","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","full_name":"Locatello, Francesco"},{"last_name":"Lacoste","first_name":"Alexandre","full_name":"Lacoste, Alexandre"},{"full_name":"Bengio, Yoshua","last_name":"Bengio","first_name":"Yoshua"},{"full_name":"Pal, Chris","first_name":"Chris","last_name":"Pal"},{"first_name":"Li Erran","last_name":"Li","full_name":"Li, Li Erran"},{"full_name":"Schölkopf, Bernhard","last_name":"Schölkopf","first_name":"Bernhard"}],"oa_version":"Preprint"},{"date_published":"2022-10-04T00:00:00Z","month":"10","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication_status":"submitted","date_updated":"2024-02-12T09:57:14Z","citation":{"short":"A. Norelli, M. Fumero, V. Maiorca, L. Moschella, E. Rodolà, F. Locatello, ArXiv (n.d.).","apa":"Norelli, A., Fumero, M., Maiorca, V., Moschella, L., Rodolà, E., &#38; Locatello, F. (n.d.). ASIF: Coupled data turns unimodal models to multimodal without training. <i>arXiv</i>. <a href=\"https://doi.org/10.48550/arXiv.2210.01738\">https://doi.org/10.48550/arXiv.2210.01738</a>","chicago":"Norelli, Antonio, Marco Fumero, Valentino Maiorca, Luca Moschella, Emanuele Rodolà, and Francesco Locatello. “ASIF: Coupled Data Turns Unimodal Models to Multimodal without Training.” <i>ArXiv</i>, n.d. <a href=\"https://doi.org/10.48550/arXiv.2210.01738\">https://doi.org/10.48550/arXiv.2210.01738</a>.","ista":"Norelli A, Fumero M, Maiorca V, Moschella L, Rodolà E, Locatello F. ASIF: Coupled data turns unimodal models to multimodal without training. arXiv, 2210.01738.","ama":"Norelli A, Fumero M, Maiorca V, Moschella L, Rodolà E, Locatello F. ASIF: Coupled data turns unimodal models to multimodal without training. <i>arXiv</i>. doi:<a href=\"https://doi.org/10.48550/arXiv.2210.01738\">10.48550/arXiv.2210.01738</a>","mla":"Norelli, Antonio, et al. “ASIF: Coupled Data Turns Unimodal Models to Multimodal without Training.” <i>ArXiv</i>, 2210.01738, doi:<a href=\"https://doi.org/10.48550/arXiv.2210.01738\">10.48550/arXiv.2210.01738</a>.","ieee":"A. Norelli, M. Fumero, V. Maiorca, L. Moschella, E. Rodolà, and F. Locatello, “ASIF: Coupled data turns unimodal models to multimodal without training,” <i>arXiv</i>. ."},"abstract":[{"text":"CLIP proved that aligning visual and language spaces is key to solving many vision tasks without explicit training, but required to train image and text encoders from scratch on a huge dataset. LiT improved this by only training the text encoder and using a pre-trained vision network. In this paper, we show that a common space can be created without any training at all, using single-domain encoders (trained with or without supervision) and a much smaller amount of image-text pairs. Furthermore, our model has unique properties. Most notably, deploying a new version with updated training samples can be done in a matter of seconds. Additionally, the representations in the common space are easily interpretable as every dimension corresponds to the similarity of the input to a unique entry in the multimodal dataset. Experiments on standard zero-shot visual benchmarks demonstrate the typical transfer ability of image-text models. Overall, our method represents a simple yet surprisingly strong baseline for foundation multi-modal models, raising important questions on their data efficiency and on the role of retrieval in machine learning.","lang":"eng"}],"type":"preprint","article_number":"2210.01738","_id":"14216","oa_version":"Preprint","external_id":{"arxiv":["2210.01738"]},"author":[{"full_name":"Norelli, Antonio","first_name":"Antonio","last_name":"Norelli"},{"full_name":"Fumero, Marco","last_name":"Fumero","first_name":"Marco"},{"full_name":"Maiorca, Valentino","last_name":"Maiorca","first_name":"Valentino"},{"last_name":"Moschella","first_name":"Luca","full_name":"Moschella, Luca"},{"full_name":"Rodolà, Emanuele","first_name":"Emanuele","last_name":"Rodolà"},{"full_name":"Locatello, Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","first_name":"Francesco","orcid":"0000-0002-4850-0683","last_name":"Locatello"}],"doi":"10.48550/arXiv.2210.01738","title":"ASIF: Coupled data turns unimodal models to multimodal without training","main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2210.01738"}],"arxiv":1,"oa":1,"day":"04","department":[{"_id":"FrLo"}],"status":"public","date_created":"2023-08-22T14:22:04Z","language":[{"iso":"eng"}],"year":"2022","article_processing_charge":"No","publication":"arXiv"},{"type":"preprint","date_updated":"2023-09-11T11:49:40Z","abstract":[{"lang":"eng","text":"Although reinforcement learning has seen remarkable progress over the last years, solving robust dexterous object-manipulation tasks in multi-object settings remains a challenge. In this paper, we focus on models that can learn manipulation tasks in fixed multi-object settings and extrapolate this skill zero-shot without any drop in performance when the number of objects changes. We consider the generic task of bringing a specific cube out of a set to a goal position. We find that previous approaches, which primarily leverage attention and graph neural network-based architectures, do not generalize their skills when the number of input objects changes while scaling as K2. We propose an alternative plug-and-play module based on relational inductive biases to overcome these limitations. Besides exceeding performances in their training environment, we show that our approach, which scales linearly in K, allows agents to extrapolate and generalize zero-shot to any new object number."}],"citation":{"ista":"Mambelli D, Träuble F, Bauer S, Schölkopf B, Locatello F. Compositional multi-object reinforcement learning with linear relation networks. arXiv, 2201.13388.","chicago":"Mambelli, Davide, Frederik Träuble, Stefan Bauer, Bernhard Schölkopf, and Francesco Locatello. “Compositional Multi-Object Reinforcement Learning with Linear Relation Networks.” <i>ArXiv</i>, n.d. <a href=\"https://doi.org/10.48550/arXiv.2201.13388\">https://doi.org/10.48550/arXiv.2201.13388</a>.","apa":"Mambelli, D., Träuble, F., Bauer, S., Schölkopf, B., &#38; Locatello, F. (n.d.). Compositional multi-object reinforcement learning with linear relation networks. <i>arXiv</i>. <a href=\"https://doi.org/10.48550/arXiv.2201.13388\">https://doi.org/10.48550/arXiv.2201.13388</a>","short":"D. Mambelli, F. Träuble, S. Bauer, B. Schölkopf, F. Locatello, ArXiv (n.d.).","ieee":"D. Mambelli, F. Träuble, S. Bauer, B. Schölkopf, and F. Locatello, “Compositional multi-object reinforcement learning with linear relation networks,” <i>arXiv</i>. .","mla":"Mambelli, Davide, et al. “Compositional Multi-Object Reinforcement Learning with Linear Relation Networks.” <i>ArXiv</i>, 2201.13388, doi:<a href=\"https://doi.org/10.48550/arXiv.2201.13388\">10.48550/arXiv.2201.13388</a>.","ama":"Mambelli D, Träuble F, Bauer S, Schölkopf B, Locatello F. Compositional multi-object reinforcement learning with linear relation networks. <i>arXiv</i>. doi:<a href=\"https://doi.org/10.48550/arXiv.2201.13388\">10.48550/arXiv.2201.13388</a>"},"_id":"14220","article_number":"2201.13388","publication_status":"submitted","date_published":"2022-01-31T00:00:00Z","month":"01","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","doi":"10.48550/arXiv.2201.13388","external_id":{"arxiv":["2201.13388"]},"author":[{"first_name":"Davide","last_name":"Mambelli","full_name":"Mambelli, Davide"},{"first_name":"Frederik","last_name":"Träuble","full_name":"Träuble, Frederik"},{"full_name":"Bauer, Stefan","last_name":"Bauer","first_name":"Stefan"},{"first_name":"Bernhard","last_name":"Schölkopf","full_name":"Schölkopf, Bernhard"},{"full_name":"Locatello, Francesco","id":"26cfd52f-2483-11ee-8040-88983bcc06d4","last_name":"Locatello","orcid":"0000-0002-4850-0683","first_name":"Francesco"}],"oa_version":"Preprint","day":"31","department":[{"_id":"FrLo"}],"main_file_link":[{"url":"https://doi.org/10.48550/arXiv.2201.13388","open_access":"1"}],"title":"Compositional multi-object reinforcement learning with linear relation networks","oa":1,"arxiv":1,"extern":"1","article_processing_charge":"No","publication":"arXiv","date_created":"2023-08-22T14:23:16Z","status":"public","language":[{"iso":"eng"}],"year":"2022"},{"publication_status":"published","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","abstract":[{"lang":"eng","text":"Purpose: The mediator (MED) multisubunit-complex modulates the activity of the transcriptional machinery, and genetic defects in different MED subunits (17, 20, 27) have been implicated in neurologic diseases. In this study, we identified a recurrent homozygous variant in MED11 (c.325C>T; p.Arg109Ter) in 7 affected individuals from 5 unrelated families. Methods: To investigate the genetic cause of the disease, exome or genome sequencing were performed in 5 unrelated families identified via different research networks and Matchmaker Exchange. Deep clinical and brain imaging evaluations were performed by clinical pediatric neurologists and neuroradiologists. The functional effect of the candidate variant on both MED11 RNA and protein was assessed using reverse transcriptase polymerase chain reaction and western blotting using fibroblast cell lines derived from 1 affected individual and controls and through computational approaches. Knockouts in zebrafish were generated using clustered regularly interspaced short palindromic repeats/Cas9. Results: The disease was characterized by microcephaly, profound neurodevelopmental impairment, exaggerated startle response, myoclonic seizures, progressive widespread neurodegeneration, and premature death. Functional studies on patient-derived fibroblasts did not show a loss of protein function but rather disruption of the C-terminal of MED11, likely impairing binding to other MED subunits. A zebrafish knockout model recapitulates key clinical phenotypes. Conclusion: Loss of the C-terminal of MED subunit 11 may affect its binding efficiency to other MED subunits, thus implicating the MED-complex stability in brain development and neurodegeneration. (C) 2022 The Authors. Published by Elsevier Inc. on behalf of American College of Medical Genetics and Genomics."}],"_id":"14355","publication_identifier":{"issn":["1098-3600"]},"volume":24,"author":[{"full_name":"Cali, Elisa","last_name":"Cali","first_name":"Elisa"},{"full_name":"Lin, Sheng-Jia","last_name":"Lin","first_name":"Sheng-Jia"},{"full_name":"Rocca, Clarissa","last_name":"Rocca","first_name":"Clarissa"},{"full_name":"Sahin, Yavuz","first_name":"Yavuz","last_name":"Sahin"},{"full_name":"Al Shamsi, Aisha","last_name":"Al Shamsi","first_name":"Aisha"},{"full_name":"El Chehadeh, Salima","last_name":"El Chehadeh","first_name":"Salima"},{"full_name":"Chaabouni, Myriam","first_name":"Myriam","last_name":"Chaabouni"},{"full_name":"Mankad, Kshitij","first_name":"Kshitij","last_name":"Mankad"},{"full_name":"Galanaki, Evangelia","first_name":"Evangelia","last_name":"Galanaki"},{"last_name":"Efthymiou","first_name":"Stephanie","full_name":"Efthymiou, Stephanie"},{"last_name":"Sudhakar","first_name":"Sniya","full_name":"Sudhakar, Sniya"},{"first_name":"Alkyoni","last_name":"Athanasiou-Fragkouli","full_name":"Athanasiou-Fragkouli, Alkyoni"},{"last_name":"Celik","first_name":"Tamer","full_name":"Celik, Tamer"},{"last_name":"Narli","first_name":"Nejat","full_name":"Narli, Nejat"},{"full_name":"Bianca, Sebastiano","last_name":"Bianca","first_name":"Sebastiano"},{"last_name":"Murphy","first_name":"David","full_name":"Murphy, David"},{"first_name":"Francisco Martins De Carvalho","last_name":"Moreira","full_name":"Moreira, Francisco Martins De Carvalho"},{"full_name":"Accogli, Andrea","last_name":"Accogli","first_name":"Andrea"},{"last_name":"Petree","first_name":"Cassidy","full_name":"Petree, Cassidy"},{"first_name":"Kevin","last_name":"Huang","orcid":"0000-0002-2512-7812","id":"3b3d2888-1ff6-11ee-9fa6-8f209ca91fe3","full_name":"Huang, Kevin"},{"last_name":"Monastiri","first_name":"Kamel","full_name":"Monastiri, Kamel"},{"last_name":"Edizadeh","first_name":"Masoud","full_name":"Edizadeh, Masoud"},{"full_name":"Nardello, Rosaria","first_name":"Rosaria","last_name":"Nardello"},{"last_name":"Ognibene","first_name":"Marzia","full_name":"Ognibene, Marzia"},{"first_name":"Patrizia","last_name":"De Marco","full_name":"De Marco, Patrizia"},{"last_name":"Ruggieri","first_name":"Martino","full_name":"Ruggieri, Martino"},{"full_name":"Zara, Federico","first_name":"Federico","last_name":"Zara"},{"full_name":"Striano, Pasquale","last_name":"Striano","first_name":"Pasquale"},{"first_name":"Yavuz","last_name":"Sahin","full_name":"Sahin, Yavuz"},{"full_name":"Al-Gazali, Lihadh","last_name":"Al-Gazali","first_name":"Lihadh"},{"full_name":"Warde, Marie Therese Abi","last_name":"Warde","first_name":"Marie Therese Abi"},{"last_name":"Gerard","first_name":"Benedicte","full_name":"Gerard, Benedicte"},{"last_name":"Zifarelli","first_name":"Giovanni","full_name":"Zifarelli, Giovanni"},{"first_name":"Christian","last_name":"Beetz","full_name":"Beetz, Christian"},{"first_name":"Sara","last_name":"Fortuna","full_name":"Fortuna, Sara"},{"first_name":"Miguel","last_name":"Soler","full_name":"Soler, Miguel"},{"full_name":"Valente, Enza Maria","first_name":"Enza Maria","last_name":"Valente"},{"first_name":"Gaurav","last_name":"Varshney","full_name":"Varshney, Gaurav"},{"last_name":"Maroofian","first_name":"Reza","full_name":"Maroofian, Reza"},{"last_name":"Salpietro","first_name":"Vincenzo","full_name":"Salpietro, Vincenzo"},{"full_name":"Houlden, Henry","last_name":"Houlden","first_name":"Henry"},{"full_name":"Grp, SYNaPS Study","last_name":"Grp","first_name":"SYNaPS Study"}],"quality_controlled":"1","oa":1,"issue":"10","day":"01","keyword":["Human mediator complex","MED11","MEDopathies"],"department":[{"_id":"GradSch"}],"date_created":"2023-09-20T20:57:18Z","status":"public","publisher":"Elsevier","file":[{"file_id":"14371","relation":"main_file","content_type":"application/pdf","file_size":1434037,"creator":"dernst","date_updated":"2023-09-25T08:56:06Z","success":1,"date_created":"2023-09-25T08:56:06Z","checksum":"8117175a89129eb5022d81ffe7625f9f","access_level":"open_access","file_name":"2022_GeneticsMedicine_Calin.pdf"}],"page":"2194-2203","ddc":["570"],"month":"10","date_published":"2022-10-01T00:00:00Z","scopus_import":"1","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"type":"journal_article","date_updated":"2023-09-25T08:57:07Z","has_accepted_license":"1","citation":{"short":"E. Cali, S.-J. Lin, C. Rocca, Y. Sahin, A. Al Shamsi, S. El Chehadeh, M. Chaabouni, K. Mankad, E. Galanaki, S. Efthymiou, S. Sudhakar, A. Athanasiou-Fragkouli, T. Celik, N. Narli, S. Bianca, D. Murphy, F.M.D.C. Moreira, A. Accogli, C. Petree, K. Huang, K. Monastiri, M. Edizadeh, R. Nardello, M. Ognibene, P. De Marco, M. Ruggieri, F. Zara, P. Striano, Y. Sahin, L. Al-Gazali, M.T.A. Warde, B. Gerard, G. Zifarelli, C. Beetz, S. Fortuna, M. Soler, E.M. Valente, G. Varshney, R. Maroofian, V. Salpietro, H. Houlden, Syn.S. Grp, Genetics in Medicine 24 (2022) 2194–2203.","apa":"Cali, E., Lin, S.-J., Rocca, C., Sahin, Y., Al Shamsi, A., El Chehadeh, S., … Grp, Syn. S. (2022). A homozygous MED11 C-terminal variant causes a lethal neurodegenerative disease. <i>Genetics in Medicine</i>. Elsevier. <a href=\"https://doi.org/10.1016/j.gim.2022.07.013\">https://doi.org/10.1016/j.gim.2022.07.013</a>","chicago":"Cali, Elisa, Sheng-Jia Lin, Clarissa Rocca, Yavuz Sahin, Aisha Al Shamsi, Salima El Chehadeh, Myriam Chaabouni, et al. “A Homozygous MED11 C-Terminal Variant Causes a Lethal Neurodegenerative Disease.” <i>Genetics in Medicine</i>. Elsevier, 2022. <a href=\"https://doi.org/10.1016/j.gim.2022.07.013\">https://doi.org/10.1016/j.gim.2022.07.013</a>.","ista":"Cali E, Lin S-J, Rocca C, Sahin Y, Al Shamsi A, El Chehadeh S, Chaabouni M, Mankad K, Galanaki E, Efthymiou S, Sudhakar S, Athanasiou-Fragkouli A, Celik T, Narli N, Bianca S, Murphy D, Moreira FMDC, Accogli A, Petree C, Huang K, Monastiri K, Edizadeh M, Nardello R, Ognibene M, De Marco P, Ruggieri M, Zara F, Striano P, Sahin Y, Al-Gazali L, Warde MTA, Gerard B, Zifarelli G, Beetz C, Fortuna S, Soler M, Valente EM, Varshney G, Maroofian R, Salpietro V, Houlden H, Grp SynS. 2022. A homozygous MED11 C-terminal variant causes a lethal neurodegenerative disease. Genetics in Medicine. 24(10), 2194–2203.","ama":"Cali E, Lin S-J, Rocca C, et al. A homozygous MED11 C-terminal variant causes a lethal neurodegenerative disease. <i>Genetics in Medicine</i>. 2022;24(10):2194-2203. doi:<a href=\"https://doi.org/10.1016/j.gim.2022.07.013\">10.1016/j.gim.2022.07.013</a>","mla":"Cali, Elisa, et al. “A Homozygous MED11 C-Terminal Variant Causes a Lethal Neurodegenerative Disease.” <i>Genetics in Medicine</i>, vol. 24, no. 10, Elsevier, 2022, pp. 2194–203, doi:<a href=\"https://doi.org/10.1016/j.gim.2022.07.013\">10.1016/j.gim.2022.07.013</a>.","ieee":"E. Cali <i>et al.</i>, “A homozygous MED11 C-terminal variant causes a lethal neurodegenerative disease,” <i>Genetics in Medicine</i>, vol. 24, no. 10. Elsevier, pp. 2194–2203, 2022."},"license":"https://creativecommons.org/licenses/by/4.0/","oa_version":"Published Version","file_date_updated":"2023-09-25T08:56:06Z","article_type":"original","doi":"10.1016/j.gim.2022.07.013","title":"A homozygous MED11 C-terminal variant causes a lethal neurodegenerative disease","intvolume":"        24","language":[{"iso":"eng"}],"year":"2022","extern":"1","publication":"Genetics in Medicine","article_processing_charge":"No"},{"month":"01","date_published":"2022-01-01T00:00:00Z","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication_status":"published","scopus_import":"1","date_updated":"2023-10-03T08:04:03Z","abstract":[{"lang":"eng","text":"Expander graphs (sparse but highly connected graphs) have, since their inception, been the source of deep links between Mathematics and Computer Science as well as applications to other areas. In recent years, a fascinating theory of high-dimensional expanders has begun to emerge, which is still in a formative stage but has nonetheless already lead to a number of striking results. Unlike for graphs, in higher dimensions there is a rich array of non-equivalent notions of expansion (coboundary expansion, cosystolic expansion, topological expansion, spectral expansion, etc.), with differents strengths and applications. In this talk, we will survey this landscape of high-dimensional expansion, with a focus on two main results. First, we will present Gromov’s Topological Overlap Theorem, which asserts that coboundary expansion (a quantitative version of vanishing mod 2 cohomology) implies topological expansion (roughly, the property that for every map from a simplicial complex to a manifold of the same dimension, the images of a positive fraction of the simplices have a point in common). Second, we will outline a construction of bounded degree 2-dimensional topological expanders, due to Kaufman, Kazhdan, and Lubotzky."}],"citation":{"ista":"Wagner U. 2022. High-dimensional expanders (after Gromov, Kaufman, Kazhdan, Lubotzky, and others). Bulletin de la Societe Mathematique de France. 438, 281–294.","chicago":"Wagner, Uli. “High-Dimensional Expanders (after Gromov, Kaufman, Kazhdan, Lubotzky, and Others).” <i>Bulletin de La Societe Mathematique de France</i>. Societe Mathematique de France, 2022. <a href=\"https://doi.org/10.24033/ast.1188\">https://doi.org/10.24033/ast.1188</a>.","apa":"Wagner, U. (2022). High-dimensional expanders (after Gromov, Kaufman, Kazhdan, Lubotzky, and others). <i>Bulletin de La Societe Mathematique de France</i>. Societe Mathematique de France. <a href=\"https://doi.org/10.24033/ast.1188\">https://doi.org/10.24033/ast.1188</a>","short":"U. Wagner, Bulletin de La Societe Mathematique de France 438 (2022) 281–294.","ieee":"U. Wagner, “High-dimensional expanders (after Gromov, Kaufman, Kazhdan, Lubotzky, and others),” <i>Bulletin de la Societe Mathematique de France</i>, vol. 438. Societe Mathematique de France, pp. 281–294, 2022.","mla":"Wagner, Uli. “High-Dimensional Expanders (after Gromov, Kaufman, Kazhdan, Lubotzky, and Others).” <i>Bulletin de La Societe Mathematique de France</i>, vol. 438, Societe Mathematique de France, 2022, pp. 281–94, doi:<a href=\"https://doi.org/10.24033/ast.1188\">10.24033/ast.1188</a>.","ama":"Wagner U. High-dimensional expanders (after Gromov, Kaufman, Kazhdan, Lubotzky, and others). <i>Bulletin de la Societe Mathematique de France</i>. 2022;438:281-294. doi:<a href=\"https://doi.org/10.24033/ast.1188\">10.24033/ast.1188</a>"},"type":"journal_article","_id":"14381","oa_version":"None","volume":438,"publication_identifier":{"issn":["0037-9484"],"eissn":["2102-622X"]},"author":[{"orcid":"0000-0002-1494-0568","last_name":"Wagner","first_name":"Uli","id":"36690CA2-F248-11E8-B48F-1D18A9856A87","full_name":"Wagner, Uli"}],"article_type":"original","doi":"10.24033/ast.1188","intvolume":"       438","quality_controlled":"1","title":"High-dimensional expanders (after Gromov, Kaufman, Kazhdan, Lubotzky, and others)","day":"01","department":[{"_id":"UlWa"}],"status":"public","date_created":"2023-10-01T22:01:14Z","year":"2022","language":[{"iso":"eng"}],"page":"281-294","publisher":"Societe Mathematique de France","article_processing_charge":"No","publication":"Bulletin de la Societe Mathematique de France"},{"doi":"10.1038/d41586-022-04447-0","article_type":"letter_note","oa_version":"None","date_updated":"2023-10-18T06:26:30Z","citation":{"ista":"Utzat H, Ibáñez M. 2022. Molecular engineering enables bright blue LEDs. Nature. 612(7941), 638–639.","chicago":"Utzat, Hendrik, and Maria Ibáñez. “Molecular Engineering Enables Bright Blue LEDs.” <i>Nature</i>. Springer Nature, 2022. <a href=\"https://doi.org/10.1038/d41586-022-04447-0\">https://doi.org/10.1038/d41586-022-04447-0</a>.","apa":"Utzat, H., &#38; Ibáñez, M. (2022). Molecular engineering enables bright blue LEDs. <i>Nature</i>. Springer Nature. <a href=\"https://doi.org/10.1038/d41586-022-04447-0\">https://doi.org/10.1038/d41586-022-04447-0</a>","short":"H. Utzat, M. Ibáñez, Nature 612 (2022) 638–639.","ieee":"H. Utzat and M. Ibáñez, “Molecular engineering enables bright blue LEDs,” <i>Nature</i>, vol. 612, no. 7941. Springer Nature, pp. 638–639, 2022.","mla":"Utzat, Hendrik, and Maria Ibáñez. “Molecular Engineering Enables Bright Blue LEDs.” <i>Nature</i>, vol. 612, no. 7941, Springer Nature, 2022, pp. 638–39, doi:<a href=\"https://doi.org/10.1038/d41586-022-04447-0\">10.1038/d41586-022-04447-0</a>.","ama":"Utzat H, Ibáñez M. Molecular engineering enables bright blue LEDs. <i>Nature</i>. 2022;612(7941):638-639. doi:<a href=\"https://doi.org/10.1038/d41586-022-04447-0\">10.1038/d41586-022-04447-0</a>"},"pmid":1,"type":"journal_article","date_published":"2022-12-21T00:00:00Z","month":"12","publication":"Nature","article_processing_charge":"No","language":[{"iso":"eng"}],"year":"2022","intvolume":"       612","title":"Molecular engineering enables bright blue LEDs","external_id":{"pmid":["36543947"]},"author":[{"full_name":"Utzat, Hendrik","last_name":"Utzat","first_name":"Hendrik"},{"full_name":"Ibáñez, Maria","id":"43C61214-F248-11E8-B48F-1D18A9856A87","first_name":"Maria","last_name":"Ibáñez","orcid":"0000-0001-5013-2843"}],"volume":612,"publication_identifier":{"eissn":["1476-4687"],"issn":["0028-0836"]},"abstract":[{"text":"Future LEDs could be based on lead halide perovskites. A breakthrough in preparing device-compatible solids composed of nanoscale perovskite crystals overcomes a long-standing hurdle in making blue perovskite LEDs.","lang":"eng"}],"_id":"14437","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication_status":"published","page":"638-639","publisher":"Springer Nature","status":"public","date_created":"2023-10-17T11:14:43Z","day":"21","keyword":["Multidisciplinary"],"department":[{"_id":"MaIb"}],"quality_controlled":"1","issue":"7941"},{"license":"https://creativecommons.org/publicdomain/zero/1.0/","_id":"14520","abstract":[{"lang":"eng","text":"This dataset comprises all data shown in the figures of the submitted article \"Compact vacuum gap transmon qubits: Selective and sensitive probes for superconductor surface losses\" at arxiv.org/abs/2206.14104. Additional raw data are available from the corresponding author on reasonable request."}],"date_updated":"2024-09-10T12:23:57Z","citation":{"apa":"Zemlicka, M., Redchenko, E., Peruzzo, M., Hassani, F., Trioni, A., Barzanjeh, S., &#38; Fink, J. M. (2022). Compact vacuum gap transmon qubits: Selective and sensitive probes for superconductor surface losses. Zenodo. <a href=\"https://doi.org/10.5281/ZENODO.8408897\">https://doi.org/10.5281/ZENODO.8408897</a>","short":"M. Zemlicka, E. Redchenko, M. Peruzzo, F. Hassani, A. Trioni, S. Barzanjeh, J.M. Fink, (2022).","ista":"Zemlicka M, Redchenko E, Peruzzo M, Hassani F, Trioni A, Barzanjeh S, Fink JM. 2022. Compact vacuum gap transmon qubits: Selective and sensitive probes for superconductor surface losses, Zenodo, <a href=\"https://doi.org/10.5281/ZENODO.8408897\">10.5281/ZENODO.8408897</a>.","chicago":"Zemlicka, Martin, Elena Redchenko, Matilda Peruzzo, Farid Hassani, Andrea Trioni, Shabir Barzanjeh, and Johannes M Fink. “Compact Vacuum Gap Transmon Qubits: Selective and Sensitive Probes for Superconductor Surface Losses.” Zenodo, 2022. <a href=\"https://doi.org/10.5281/ZENODO.8408897\">https://doi.org/10.5281/ZENODO.8408897</a>.","ama":"Zemlicka M, Redchenko E, Peruzzo M, et al. Compact vacuum gap transmon qubits: Selective and sensitive probes for superconductor surface losses. 2022. doi:<a href=\"https://doi.org/10.5281/ZENODO.8408897\">10.5281/ZENODO.8408897</a>","ieee":"M. Zemlicka <i>et al.</i>, “Compact vacuum gap transmon qubits: Selective and sensitive probes for superconductor surface losses.” Zenodo, 2022.","mla":"Zemlicka, Martin, et al. <i>Compact Vacuum Gap Transmon Qubits: Selective and Sensitive Probes for Superconductor Surface Losses</i>. Zenodo, 2022, doi:<a href=\"https://doi.org/10.5281/ZENODO.8408897\">10.5281/ZENODO.8408897</a>."},"has_accepted_license":"1","type":"research_data_reference","tmp":{"name":"Creative Commons Public Domain Dedication (CC0 1.0)","image":"/images/cc_0.png","short":"CC0 (1.0)","legal_code_url":"https://creativecommons.org/publicdomain/zero/1.0/legalcode"},"month":"06","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_published":"2022-06-28T00:00:00Z","ddc":["530"],"related_material":{"record":[{"relation":"used_in_publication","id":"14517","status":"public"}]},"author":[{"id":"2DCF8DE6-F248-11E8-B48F-1D18A9856A87","first_name":"Martin","last_name":"Zemlicka","full_name":"Zemlicka, Martin"},{"id":"2C21D6E8-F248-11E8-B48F-1D18A9856A87","first_name":"Elena","last_name":"Redchenko","full_name":"Redchenko, Elena"},{"full_name":"Peruzzo, Matilda","id":"3F920B30-F248-11E8-B48F-1D18A9856A87","last_name":"Peruzzo","orcid":"0000-0002-3415-4628","first_name":"Matilda"},{"id":"2AED110C-F248-11E8-B48F-1D18A9856A87","first_name":"Farid","last_name":"Hassani","orcid":"0000-0001-6937-5773","full_name":"Hassani, Farid"},{"full_name":"Trioni, Andrea","id":"42F71B44-F248-11E8-B48F-1D18A9856A87","first_name":"Andrea","last_name":"Trioni"},{"id":"2D25E1F6-F248-11E8-B48F-1D18A9856A87","last_name":"Barzanjeh","orcid":"0000-0003-0415-1423","first_name":"Shabir","full_name":"Barzanjeh, Shabir"},{"id":"4B591CBA-F248-11E8-B48F-1D18A9856A87","first_name":"Johannes M","last_name":"Fink","orcid":"0000-0001-8112-028X","full_name":"Fink, Johannes M"}],"doi":"10.5281/ZENODO.8408897","oa_version":"Published Version","department":[{"_id":"JoFi"}],"day":"28","oa":1,"main_file_link":[{"url":"https://doi.org/10.5281/ZENODO.8408897","open_access":"1"}],"title":"Compact vacuum gap transmon qubits: Selective and sensitive probes for superconductor surface losses","publisher":"Zenodo","article_processing_charge":"No","year":"2022","status":"public","date_created":"2023-11-13T08:09:10Z"},{"day":"31","department":[{"_id":"JuFi"}],"main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2203.17143"}],"title":"Quantitative convergence of the vectorial Allen-Cahn equation towards multiphase mean curvature flow","arxiv":1,"oa":1,"article_processing_charge":"No","publication":"arXiv","status":"public","date_created":"2023-11-23T09:30:02Z","year":"2022","language":[{"iso":"eng"}],"abstract":[{"text":"Phase-field models such as the Allen-Cahn equation may give rise to the formation and evolution of geometric shapes, a phenomenon that may be analyzed rigorously in suitable scaling regimes. In its sharp-interface limit, the vectorial Allen-Cahn equation with a potential with N≥3 distinct minima has been conjectured to describe the evolution of branched interfaces by multiphase mean curvature flow.\r\nIn the present work, we give a rigorous proof for this statement in two and three ambient dimensions and for a suitable class of potentials: As long as a strong solution to multiphase mean curvature flow exists, solutions to the vectorial Allen-Cahn equation with well-prepared initial data converge towards multiphase mean curvature flow in the limit of vanishing interface width parameter ε↘0. We even establish the rate of convergence O(ε1/2).\r\nOur approach is based on the gradient flow structure of the Allen-Cahn equation and its limiting motion: Building on the recent concept of \"gradient flow calibrations\" for multiphase mean curvature flow, we introduce a notion of relative entropy for the vectorial Allen-Cahn equation with multi-well potential. This enables us to overcome the limitations of other approaches, e.g. avoiding the need for a stability analysis of the Allen-Cahn operator or additional convergence hypotheses for the energy at positive times.","lang":"eng"}],"citation":{"ama":"Fischer JL, Marveggio A. Quantitative convergence of the vectorial Allen-Cahn equation towards multiphase mean curvature flow. <i>arXiv</i>. doi:<a href=\"https://doi.org/10.48550/ARXIV.2203.17143\">10.48550/ARXIV.2203.17143</a>","ieee":"J. L. Fischer and A. Marveggio, “Quantitative convergence of the vectorial Allen-Cahn equation towards multiphase mean curvature flow,” <i>arXiv</i>. .","mla":"Fischer, Julian L., and Alice Marveggio. “Quantitative Convergence of the Vectorial Allen-Cahn Equation towards Multiphase Mean Curvature Flow.” <i>ArXiv</i>, doi:<a href=\"https://doi.org/10.48550/ARXIV.2203.17143\">10.48550/ARXIV.2203.17143</a>.","apa":"Fischer, J. L., &#38; Marveggio, A. (n.d.). Quantitative convergence of the vectorial Allen-Cahn equation towards multiphase mean curvature flow. <i>arXiv</i>. <a href=\"https://doi.org/10.48550/ARXIV.2203.17143\">https://doi.org/10.48550/ARXIV.2203.17143</a>","short":"J.L. Fischer, A. Marveggio, ArXiv (n.d.).","ista":"Fischer JL, Marveggio A. Quantitative convergence of the vectorial Allen-Cahn equation towards multiphase mean curvature flow. arXiv, <a href=\"https://doi.org/10.48550/ARXIV.2203.17143\">10.48550/ARXIV.2203.17143</a>.","chicago":"Fischer, Julian L, and Alice Marveggio. “Quantitative Convergence of the Vectorial Allen-Cahn Equation towards Multiphase Mean Curvature Flow.” <i>ArXiv</i>, n.d. <a href=\"https://doi.org/10.48550/ARXIV.2203.17143\">https://doi.org/10.48550/ARXIV.2203.17143</a>."},"date_updated":"2023-11-30T13:25:02Z","type":"preprint","_id":"14597","month":"03","user_id":"8b945eb4-e2f2-11eb-945a-df72226e66a9","date_published":"2022-03-31T00:00:00Z","publication_status":"submitted","author":[{"orcid":"0000-0002-0479-558X","last_name":"Fischer","first_name":"Julian L","id":"2C12A0B0-F248-11E8-B48F-1D18A9856A87","full_name":"Fischer, Julian L"},{"full_name":"Marveggio, Alice","last_name":"Marveggio","first_name":"Alice","id":"25647992-AA84-11E9-9D75-8427E6697425"}],"external_id":{"arxiv":["2203.17143"]},"related_material":{"record":[{"relation":"dissertation_contains","id":"14587","status":"public"}]},"doi":"10.48550/ARXIV.2203.17143","ec_funded":1,"project":[{"call_identifier":"H2020","grant_number":"948819","_id":"0aa76401-070f-11eb-9043-b5bb049fa26d","name":"Bridging Scales in Random Materials"}],"oa_version":"Preprint"},{"oa_version":"Preprint","project":[{"_id":"0599E47C-7A3F-11EA-A408-12923DDC885E","name":"Formal Methods for Stochastic Models: Algorithms and Applications","call_identifier":"H2020","grant_number":"863818"},{"name":"Vigilant Algorithmic Monitoring of Software","_id":"62781420-2b32-11ec-9570-8d9b63373d4d","grant_number":"101020093","call_identifier":"H2020"},{"call_identifier":"H2020","grant_number":"665385","name":"International IST Doctoral Program","_id":"2564DBCA-B435-11E9-9278-68D0E5697425"}],"ec_funded":1,"related_material":{"record":[{"relation":"dissertation_contains","id":"14539","status":"public"},{"relation":"later_version","id":"14830","status":"public"}]},"external_id":{"arxiv":["2210.05308"]},"author":[{"orcid":"0000-0002-4681-1699","last_name":"Zikelic","first_name":"Dorde","id":"294AA7A6-F248-11E8-B48F-1D18A9856A87","full_name":"Zikelic, Dorde"},{"first_name":"Mathias","last_name":"Lechner","id":"3DC22916-F248-11E8-B48F-1D18A9856A87","full_name":"Lechner, Mathias"},{"first_name":"Thomas A","orcid":"0000-0002-2985-7724","last_name":"Henzinger","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","full_name":"Henzinger, Thomas A"},{"id":"2E5DCA20-F248-11E8-B48F-1D18A9856A87","first_name":"Krishnendu","orcid":"0000-0002-4561-241X","last_name":"Chatterjee","full_name":"Chatterjee, Krishnendu"}],"doi":"10.48550/ARXIV.2210.05308","tmp":{"legal_code_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","short":"CC BY-SA (4.0)","image":"/images/cc_by_sa.png","name":"Creative Commons Attribution-ShareAlike 4.0 International Public License (CC BY-SA 4.0)"},"date_published":"2022-11-29T00:00:00Z","user_id":"8b945eb4-e2f2-11eb-945a-df72226e66a9","month":"11","publication_status":"submitted","_id":"14600","license":"https://creativecommons.org/licenses/by-sa/4.0/","citation":{"apa":"Zikelic, D., Lechner, M., Henzinger, T. A., &#38; Chatterjee, K. (n.d.). Learning control policies for stochastic systems with reach-avoid guarantees. <i>arXiv</i>. <a href=\"https://doi.org/10.48550/ARXIV.2210.05308\">https://doi.org/10.48550/ARXIV.2210.05308</a>","short":"D. Zikelic, M. Lechner, T.A. Henzinger, K. Chatterjee, ArXiv (n.d.).","ista":"Zikelic D, Lechner M, Henzinger TA, Chatterjee K. Learning control policies for stochastic systems with reach-avoid guarantees. arXiv, <a href=\"https://doi.org/10.48550/ARXIV.2210.05308\">10.48550/ARXIV.2210.05308</a>.","chicago":"Zikelic, Dorde, Mathias Lechner, Thomas A Henzinger, and Krishnendu Chatterjee. “Learning Control Policies for Stochastic Systems with Reach-Avoid Guarantees.” <i>ArXiv</i>, n.d. <a href=\"https://doi.org/10.48550/ARXIV.2210.05308\">https://doi.org/10.48550/ARXIV.2210.05308</a>.","ama":"Zikelic D, Lechner M, Henzinger TA, Chatterjee K. Learning control policies for stochastic systems with reach-avoid guarantees. <i>arXiv</i>. doi:<a href=\"https://doi.org/10.48550/ARXIV.2210.05308\">10.48550/ARXIV.2210.05308</a>","ieee":"D. Zikelic, M. Lechner, T. A. Henzinger, and K. Chatterjee, “Learning control policies for stochastic systems with reach-avoid guarantees,” <i>arXiv</i>. .","mla":"Zikelic, Dorde, et al. “Learning Control Policies for Stochastic Systems with Reach-Avoid Guarantees.” <i>ArXiv</i>, doi:<a href=\"https://doi.org/10.48550/ARXIV.2210.05308\">10.48550/ARXIV.2210.05308</a>."},"date_updated":"2025-07-14T09:10:02Z","abstract":[{"lang":"eng","text":"We study the problem of learning controllers for discrete-time non-linear stochastic dynamical systems with formal reach-avoid guarantees. This work presents the first method for providing formal reach-avoid guarantees, which combine and generalize stability and safety guarantees, with a tolerable probability threshold $p\\in[0,1]$ over the infinite time horizon. Our method leverages advances in machine learning literature and it represents formal certificates as neural networks. In particular, we learn a certificate in the form of a reach-avoid supermartingale (RASM), a novel notion that we introduce in this work. Our RASMs provide reachability and avoidance guarantees by imposing constraints on what can be viewed as a stochastic extension of level sets of Lyapunov functions for deterministic systems. Our approach solves several important problems -- it can be used to learn a control policy from scratch, to verify a reach-avoid specification for a fixed control policy, or to fine-tune a pre-trained policy if it does not satisfy the reach-avoid specification. We validate our approach on $3$ stochastic non-linear reinforcement learning tasks."}],"type":"preprint","language":[{"iso":"eng"}],"year":"2022","status":"public","date_created":"2023-11-24T13:10:09Z","article_processing_charge":"No","publication":"arXiv","arxiv":1,"oa":1,"title":"Learning control policies for stochastic systems with reach-avoid guarantees","main_file_link":[{"url":"https://arxiv.org/abs/2210.05308","open_access":"1"}],"department":[{"_id":"KrCh"},{"_id":"ToHe"}],"day":"29"}]