--- _id: '14105' abstract: - lang: eng text: "Despite their recent success, deep neural networks continue to perform poorly when they encounter distribution shifts at test time. Many recently proposed approaches try to counter this by aligning the model to the new distribution prior to inference. With no labels available this requires unsupervised objectives to adapt the model on the observed test data. In this paper, we propose Test-Time SelfTraining (TeST): a technique that takes as input a model trained on some source data and a novel data distribution at test time, and learns invariant and robust representations using a student-teacher framework. We find that models adapted using TeST significantly improve over baseline testtime adaptation algorithms. TeST achieves competitive performance to modern domain adaptation algorithms [4, 43], while having access to 5-10x less data at time of adaption. We thoroughly evaluate a variety of baselines on two tasks:\r\nobject detection and image segmentation and find that models adapted with TeST. We find that TeST sets the new stateof-the art for test-time domain adaptation algorithms. " article_processing_charge: No arxiv: 1 author: - first_name: Samarth full_name: Sinha, Samarth last_name: Sinha - first_name: Peter full_name: Gehler, Peter last_name: Gehler - first_name: Francesco full_name: Locatello, Francesco id: 26cfd52f-2483-11ee-8040-88983bcc06d4 last_name: Locatello orcid: 0000-0002-4850-0683 - first_name: Bernt full_name: Schiele, Bernt last_name: Schiele citation: ama: 'Sinha S, Gehler P, Locatello F, Schiele B. TeST: Test-time Self-Training under distribution shift. In: 2023 IEEE/CVF Winter Conference on Applications of Computer Vision. Institute of Electrical and Electronics Engineers; 2023. doi:10.1109/wacv56688.2023.00278' apa: 'Sinha, S., Gehler, P., Locatello, F., & Schiele, B. (2023). TeST: Test-time Self-Training under distribution shift. In 2023 IEEE/CVF Winter Conference on Applications of Computer Vision. Waikoloa, HI, United States: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/wacv56688.2023.00278' chicago: 'Sinha, Samarth, Peter Gehler, Francesco Locatello, and Bernt Schiele. “TeST: Test-Time Self-Training under Distribution Shift.” In 2023 IEEE/CVF Winter Conference on Applications of Computer Vision. Institute of Electrical and Electronics Engineers, 2023. https://doi.org/10.1109/wacv56688.2023.00278.' ieee: 'S. Sinha, P. Gehler, F. Locatello, and B. Schiele, “TeST: Test-time Self-Training under distribution shift,” in 2023 IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, United States, 2023.' ista: 'Sinha S, Gehler P, Locatello F, Schiele B. 2023. TeST: Test-time Self-Training under distribution shift. 2023 IEEE/CVF Winter Conference on Applications of Computer Vision. WACV: Winter Conference on Applications of Computer Vision.' mla: 'Sinha, Samarth, et al. “TeST: Test-Time Self-Training under Distribution Shift.” 2023 IEEE/CVF Winter Conference on Applications of Computer Vision, Institute of Electrical and Electronics Engineers, 2023, doi:10.1109/wacv56688.2023.00278.' short: S. Sinha, P. Gehler, F. Locatello, B. Schiele, in:, 2023 IEEE/CVF Winter Conference on Applications of Computer Vision, Institute of Electrical and Electronics Engineers, 2023. conference: end_date: 2023-01-07 location: Waikoloa, HI, United States name: 'WACV: Winter Conference on Applications of Computer Vision' start_date: 2023-01-02 date_created: 2023-08-21T12:11:38Z date_published: 2023-02-06T00:00:00Z date_updated: 2023-09-06T10:26:56Z day: '06' department: - _id: FrLo doi: 10.1109/wacv56688.2023.00278 extern: '1' external_id: arxiv: - '2209.11459' language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/2209.11459 month: '02' oa: 1 oa_version: Preprint publication: 2023 IEEE/CVF Winter Conference on Applications of Computer Vision publication_identifier: eissn: - 2642-9381 isbn: - '9781665493475' publication_status: published publisher: Institute of Electrical and Electronics Engineers quality_controlled: '1' scopus_import: '1' status: public title: 'TeST: Test-time Self-Training under distribution shift' type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2023' ... --- _id: '14192' abstract: - lang: eng text: For the Fröhlich model of the large polaron, we prove that the ground state energy as a function of the total momentum has a unique global minimum at momentum zero. This implies the non-existence of a ground state of the translation invariant Fröhlich Hamiltonian and thus excludes the possibility of a localization transition at finite coupling. acknowledgement: D.M. and K.M. thank Robert Seiringer for helpful discussions. Open access funding provided by Institute of Science and Technology (IST Austria). Financial support from the Agence Nationale de la Recherche (ANR) through the projects ANR-17-CE40-0016, ANR-17-CE40-0007-01, ANR-17-EURE-0002 (J.L.) and from the European Union’s Horizon 2020 research and innovation programme under the Maria Skłodowska-Curie grant agreement No. 665386 (K.M.) is gratefully acknowledged. article_number: '17' article_processing_charge: Yes (via OA deal) article_type: original arxiv: 1 author: - first_name: Jonas full_name: Lampart, Jonas last_name: Lampart - first_name: David Johannes full_name: Mitrouskas, David Johannes id: cbddacee-2b11-11eb-a02e-a2e14d04e52d last_name: Mitrouskas - first_name: Krzysztof full_name: Mysliwy, Krzysztof id: 316457FC-F248-11E8-B48F-1D18A9856A87 last_name: Mysliwy citation: ama: Lampart J, Mitrouskas DJ, Mysliwy K. On the global minimum of the energy–momentum relation for the polaron. Mathematical Physics, Analysis and Geometry. 2023;26(3). doi:10.1007/s11040-023-09460-x apa: Lampart, J., Mitrouskas, D. J., & Mysliwy, K. (2023). On the global minimum of the energy–momentum relation for the polaron. Mathematical Physics, Analysis and Geometry. Springer Nature. https://doi.org/10.1007/s11040-023-09460-x chicago: Lampart, Jonas, David Johannes Mitrouskas, and Krzysztof Mysliwy. “On the Global Minimum of the Energy–Momentum Relation for the Polaron.” Mathematical Physics, Analysis and Geometry. Springer Nature, 2023. https://doi.org/10.1007/s11040-023-09460-x. ieee: J. Lampart, D. J. Mitrouskas, and K. Mysliwy, “On the global minimum of the energy–momentum relation for the polaron,” Mathematical Physics, Analysis and Geometry, vol. 26, no. 3. Springer Nature, 2023. ista: Lampart J, Mitrouskas DJ, Mysliwy K. 2023. On the global minimum of the energy–momentum relation for the polaron. Mathematical Physics, Analysis and Geometry. 26(3), 17. mla: Lampart, Jonas, et al. “On the Global Minimum of the Energy–Momentum Relation for the Polaron.” Mathematical Physics, Analysis and Geometry, vol. 26, no. 3, 17, Springer Nature, 2023, doi:10.1007/s11040-023-09460-x. short: J. Lampart, D.J. Mitrouskas, K. Mysliwy, Mathematical Physics, Analysis and Geometry 26 (2023). date_created: 2023-08-22T14:09:47Z date_published: 2023-07-26T00:00:00Z date_updated: 2023-12-13T12:16:19Z day: '26' ddc: - '510' department: - _id: RoSe doi: 10.1007/s11040-023-09460-x external_id: arxiv: - '2206.14708' isi: - '001032992600001' file: - access_level: open_access checksum: f0941cc66cb3ed06a12ca4b7e356cfd6 content_type: application/pdf creator: dernst date_created: 2023-08-23T10:59:15Z date_updated: 2023-08-23T10:59:15Z file_id: '14225' file_name: 2023_MathPhysics_Lampart.pdf file_size: 317026 relation: main_file success: 1 file_date_updated: 2023-08-23T10:59:15Z has_accepted_license: '1' intvolume: ' 26' isi: 1 issue: '3' keyword: - Geometry and Topology - Mathematical Physics language: - iso: eng month: '07' oa: 1 oa_version: Published Version publication: Mathematical Physics, Analysis and Geometry publication_identifier: eissn: - 1572-9656 issn: - 1385-0172 publication_status: published publisher: Springer Nature quality_controlled: '1' scopus_import: '1' status: public title: On the global minimum of the energy–momentum relation for the polaron tmp: image: /images/cc_by.png legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0) short: CC BY (4.0) type: journal_article user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 volume: 26 year: '2023' ... --- _id: '14207' abstract: - lang: eng text: The binding problem in human cognition, concerning how the brain represents and connects objects within a fixed network of neural connections, remains a subject of intense debate. Most machine learning efforts addressing this issue in an unsupervised setting have focused on slot-based methods, which may be limiting due to their discrete nature and difficulty to express uncertainty. Recently, the Complex AutoEncoder was proposed as an alternative that learns continuous and distributed object-centric representations. However, it is only applicable to simple toy data. In this paper, we present Rotating Features, a generalization of complex-valued features to higher dimensions, and a new evaluation procedure for extracting objects from distributed representations. Additionally, we show the applicability of our approach to pre-trained features. Together, these advancements enable us to scale distributed object-centric representations from simple toy to real-world data. We believe this work advances a new paradigm for addressing the binding problem in machine learning and has the potential to inspire further innovation in the field. article_number: '2306.00600' article_processing_charge: No arxiv: 1 author: - first_name: Sindy full_name: Löwe, Sindy last_name: Löwe - first_name: Phillip full_name: Lippe, Phillip last_name: Lippe - first_name: Francesco full_name: Locatello, Francesco id: 26cfd52f-2483-11ee-8040-88983bcc06d4 last_name: Locatello orcid: 0000-0002-4850-0683 - first_name: Max full_name: Welling, Max last_name: Welling citation: ama: Löwe S, Lippe P, Locatello F, Welling M. Rotating features for object discovery. arXiv. doi:10.48550/arXiv.2306.00600 apa: Löwe, S., Lippe, P., Locatello, F., & Welling, M. (n.d.). Rotating features for object discovery. arXiv. https://doi.org/10.48550/arXiv.2306.00600 chicago: Löwe, Sindy, Phillip Lippe, Francesco Locatello, and Max Welling. “Rotating Features for Object Discovery.” ArXiv, n.d. https://doi.org/10.48550/arXiv.2306.00600. ieee: S. Löwe, P. Lippe, F. Locatello, and M. Welling, “Rotating features for object discovery,” arXiv. . ista: Löwe S, Lippe P, Locatello F, Welling M. Rotating features for object discovery. arXiv, 2306.00600. mla: Löwe, Sindy, et al. “Rotating Features for Object Discovery.” ArXiv, 2306.00600, doi:10.48550/arXiv.2306.00600. short: S. Löwe, P. Lippe, F. Locatello, M. Welling, ArXiv (n.d.). date_created: 2023-08-22T14:18:00Z date_published: 2023-06-01T00:00:00Z date_updated: 2024-02-12T09:53:44Z day: '01' department: - _id: FrLo doi: 10.48550/arXiv.2306.00600 external_id: arxiv: - '2306.00600' language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/2306.00600 month: '06' oa: 1 oa_version: Preprint publication: arXiv publication_status: submitted status: public title: Rotating features for object discovery type: preprint user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2023' ... --- _id: '14208' abstract: - lang: eng text: This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification while obtaining (nearly) zero-training error under the lazy training regime. For this purpose, we unify three interrelated concepts of overparameterization, benign overfitting, and the Lipschitz constant of DNNs. Our results indicate that interpolating with smoother functions leads to better generalization. Furthermore, we investigate the special case where interpolating smooth ground-truth functions is performed by DNNs under the Neural Tangent Kernel (NTK) regime for generalization. Our result demonstrates that the generalization error converges to a constant order that only depends on label noise and initialization noise, which theoretically verifies benign overfitting. Our analysis provides a tight lower bound on the normalized margin under non-smooth activation functions, as well as the minimum eigenvalue of NTK under high-dimensional settings, which has its own interest in learning theory. alternative_title: - PMLR article_processing_charge: No arxiv: 1 author: - first_name: Zhenyu full_name: Zhu, Zhenyu last_name: Zhu - first_name: Fanghui full_name: Liu, Fanghui last_name: Liu - first_name: Grigorios G full_name: Chrysos, Grigorios G last_name: Chrysos - first_name: Francesco full_name: Locatello, Francesco id: 26cfd52f-2483-11ee-8040-88983bcc06d4 last_name: Locatello orcid: 0000-0002-4850-0683 - first_name: Volkan full_name: Cevher, Volkan last_name: Cevher citation: ama: 'Zhu Z, Liu F, Chrysos GG, Locatello F, Cevher V. Benign overfitting in deep neural networks under lazy training. In: Proceedings of the 40th International Conference on Machine Learning. Vol 202. ML Research Press; 2023:43105-43128.' apa: 'Zhu, Z., Liu, F., Chrysos, G. G., Locatello, F., & Cevher, V. (2023). Benign overfitting in deep neural networks under lazy training. In Proceedings of the 40th International Conference on Machine Learning (Vol. 202, pp. 43105–43128). Honolulu, Hawaii, United States: ML Research Press.' chicago: Zhu, Zhenyu, Fanghui Liu, Grigorios G Chrysos, Francesco Locatello, and Volkan Cevher. “Benign Overfitting in Deep Neural Networks under Lazy Training.” In Proceedings of the 40th International Conference on Machine Learning, 202:43105–28. ML Research Press, 2023. ieee: Z. Zhu, F. Liu, G. G. Chrysos, F. Locatello, and V. Cevher, “Benign overfitting in deep neural networks under lazy training,” in Proceedings of the 40th International Conference on Machine Learning, Honolulu, Hawaii, United States, 2023, vol. 202, pp. 43105–43128. ista: Zhu Z, Liu F, Chrysos GG, Locatello F, Cevher V. 2023. Benign overfitting in deep neural networks under lazy training. Proceedings of the 40th International Conference on Machine Learning. International Conference on Machine Learning, PMLR, vol. 202, 43105–43128. mla: Zhu, Zhenyu, et al. “Benign Overfitting in Deep Neural Networks under Lazy Training.” Proceedings of the 40th International Conference on Machine Learning, vol. 202, ML Research Press, 2023, pp. 43105–28. short: Z. Zhu, F. Liu, G.G. Chrysos, F. Locatello, V. Cevher, in:, Proceedings of the 40th International Conference on Machine Learning, ML Research Press, 2023, pp. 43105–43128. conference: end_date: 2023-07-29 location: Honolulu, Hawaii, United States name: International Conference on Machine Learning start_date: 2023-07-23 date_created: 2023-08-22T14:18:18Z date_published: 2023-05-30T00:00:00Z date_updated: 2023-09-13T08:46:46Z day: '30' department: - _id: FrLo extern: '1' external_id: arxiv: - '2305.19377' intvolume: ' 202' language: - iso: eng main_file_link: - open_access: '1' url: https://doi.org/10.48550/arXiv.2305.19377 month: '05' oa: 1 oa_version: Preprint page: 43105-43128 publication: Proceedings of the 40th International Conference on Machine Learning publication_status: published publisher: ML Research Press quality_controlled: '1' status: public title: Benign overfitting in deep neural networks under lazy training type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 volume: 202 year: '2023' ... --- _id: '14209' abstract: - lang: eng text: Diffusion models excel at generating photorealistic images from text-queries. Naturally, many approaches have been proposed to use these generative abilities to augment training datasets for downstream tasks, such as classification. However, diffusion models are themselves trained on large noisily supervised, but nonetheless, annotated datasets. It is an open question whether the generalization capabilities of diffusion models beyond using the additional data of the pre-training process for augmentation lead to improved downstream performance. We perform a systematic evaluation of existing methods to generate images from diffusion models and study new extensions to assess their benefit for data augmentation. While we find that personalizing diffusion models towards the target data outperforms simpler prompting strategies, we also show that using the training data of the diffusion model alone, via a simple nearest neighbor retrieval procedure, leads to even stronger downstream performance. Overall, our study probes the limitations of diffusion models for data augmentation but also highlights its potential in generating new training data to improve performance on simple downstream vision tasks. article_number: '2304.10253' article_processing_charge: No arxiv: 1 author: - first_name: Max F. full_name: Burg, Max F. last_name: Burg - first_name: Florian full_name: Wenzel, Florian last_name: Wenzel - first_name: Dominik full_name: Zietlow, Dominik last_name: Zietlow - first_name: Max full_name: Horn, Max last_name: Horn - first_name: Osama full_name: Makansi, Osama last_name: Makansi - first_name: Francesco full_name: Locatello, Francesco id: 26cfd52f-2483-11ee-8040-88983bcc06d4 last_name: Locatello orcid: 0000-0002-4850-0683 - first_name: Chris full_name: Russell, Chris last_name: Russell citation: ama: Burg MF, Wenzel F, Zietlow D, et al. A data augmentation perspective on diffusion models and retrieval. arXiv. doi:10.48550/arXiv.2304.10253 apa: Burg, M. F., Wenzel, F., Zietlow, D., Horn, M., Makansi, O., Locatello, F., & Russell, C. (n.d.). A data augmentation perspective on diffusion models and retrieval. arXiv. https://doi.org/10.48550/arXiv.2304.10253 chicago: Burg, Max F., Florian Wenzel, Dominik Zietlow, Max Horn, Osama Makansi, Francesco Locatello, and Chris Russell. “A Data Augmentation Perspective on Diffusion Models and Retrieval.” ArXiv, n.d. https://doi.org/10.48550/arXiv.2304.10253. ieee: M. F. Burg et al., “A data augmentation perspective on diffusion models and retrieval,” arXiv. . ista: Burg MF, Wenzel F, Zietlow D, Horn M, Makansi O, Locatello F, Russell C. A data augmentation perspective on diffusion models and retrieval. arXiv, 2304.10253. mla: Burg, Max F., et al. “A Data Augmentation Perspective on Diffusion Models and Retrieval.” ArXiv, 2304.10253, doi:10.48550/arXiv.2304.10253. short: M.F. Burg, F. Wenzel, D. Zietlow, M. Horn, O. Makansi, F. Locatello, C. Russell, ArXiv (n.d.). date_created: 2023-08-22T14:18:43Z date_published: 2023-04-20T00:00:00Z date_updated: 2023-09-13T08:51:56Z day: '20' department: - _id: FrLo doi: 10.48550/arXiv.2304.10253 extern: '1' external_id: arxiv: - '2304.10253' language: - iso: eng main_file_link: - open_access: '1' url: https://doi.org/10.48550/arXiv.2304.10253 month: '04' oa: 1 oa_version: Preprint publication: arXiv publication_status: submitted status: public title: A data augmentation perspective on diffusion models and retrieval type: preprint user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2023' ... --- _id: '14210' abstract: - lang: eng text: Recovering the latent factors of variation of high dimensional data has so far focused on simple synthetic settings. Mostly building on unsupervised and weakly-supervised objectives, prior work missed out on the positive implications for representation learning on real world data. In this work, we propose to leverage knowledge extracted from a diversified set of supervised tasks to learn a common disentangled representation. Assuming each supervised task only depends on an unknown subset of the factors of variation, we disentangle the feature space of a supervised multi-task model, with features activating sparsely across different tasks and information being shared as appropriate. Importantly, we never directly observe the factors of variations but establish that access to multiple tasks is sufficient for identifiability under sufficiency and minimality assumptions. We validate our approach on six real world distribution shift benchmarks, and different data modalities (images, text), demonstrating how disentangled representations can be transferred to real settings. article_number: '2304.07939' article_processing_charge: No arxiv: 1 author: - first_name: Marco full_name: Fumero, Marco last_name: Fumero - first_name: Florian full_name: Wenzel, Florian last_name: Wenzel - first_name: Luca full_name: Zancato, Luca last_name: Zancato - first_name: Alessandro full_name: Achille, Alessandro last_name: Achille - first_name: Emanuele full_name: Rodolà, Emanuele last_name: Rodolà - first_name: Stefano full_name: Soatto, Stefano last_name: Soatto - first_name: Bernhard full_name: Schölkopf, Bernhard last_name: Schölkopf - first_name: Francesco full_name: Locatello, Francesco id: 26cfd52f-2483-11ee-8040-88983bcc06d4 last_name: Locatello orcid: 0000-0002-4850-0683 citation: ama: Fumero M, Wenzel F, Zancato L, et al. Leveraging sparse and shared feature activations for disentangled representation learning. arXiv. doi:10.48550/arXiv.2304.07939 apa: Fumero, M., Wenzel, F., Zancato, L., Achille, A., Rodolà, E., Soatto, S., … Locatello, F. (n.d.). Leveraging sparse and shared feature activations for disentangled representation learning. arXiv. https://doi.org/10.48550/arXiv.2304.07939 chicago: Fumero, Marco, Florian Wenzel, Luca Zancato, Alessandro Achille, Emanuele Rodolà, Stefano Soatto, Bernhard Schölkopf, and Francesco Locatello. “Leveraging Sparse and Shared Feature Activations for Disentangled Representation Learning.” ArXiv, n.d. https://doi.org/10.48550/arXiv.2304.07939. ieee: M. Fumero et al., “Leveraging sparse and shared feature activations for disentangled representation learning,” arXiv. . ista: Fumero M, Wenzel F, Zancato L, Achille A, Rodolà E, Soatto S, Schölkopf B, Locatello F. Leveraging sparse and shared feature activations for disentangled representation learning. arXiv, 2304.07939. mla: Fumero, Marco, et al. “Leveraging Sparse and Shared Feature Activations for Disentangled Representation Learning.” ArXiv, 2304.07939, doi:10.48550/arXiv.2304.07939. short: M. Fumero, F. Wenzel, L. Zancato, A. Achille, E. Rodolà, S. Soatto, B. Schölkopf, F. Locatello, ArXiv (n.d.). date_created: 2023-08-22T14:19:03Z date_published: 2023-04-17T00:00:00Z date_updated: 2024-02-12T09:55:48Z day: '17' department: - _id: FrLo doi: 10.48550/arXiv.2304.07939 external_id: arxiv: - '2304.07939' language: - iso: eng main_file_link: - open_access: '1' url: https://doi.org/10.48550/arXiv.2304.07939 month: '04' oa: 1 oa_version: Preprint publication: arXiv publication_status: submitted status: public title: Leveraging sparse and shared feature activations for disentangled representation learning type: preprint user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2023' ... --- _id: '14211' abstract: - lang: eng text: 'Causal discovery methods are intrinsically constrained by the set of assumptions needed to ensure structure identifiability. Moreover additional restrictions are often imposed in order to simplify the inference task: this is the case for the Gaussian noise assumption on additive non-linear models, which is common to many causal discovery approaches. In this paper we show the shortcomings of inference under this hypothesis, analyzing the risk of edge inversion under violation of Gaussianity of the noise terms. Then, we propose a novel method for inferring the topological ordering of the variables in the causal graph, from data generated according to an additive non-linear model with a generic noise distribution. This leads to NoGAM (Not only Gaussian Additive noise Models), a causal discovery algorithm with a minimal set of assumptions and state of the art performance, experimentally benchmarked on synthetic data.' article_processing_charge: No arxiv: 1 author: - first_name: Francesco full_name: Montagna, Francesco last_name: Montagna - first_name: Nicoletta full_name: Noceti, Nicoletta last_name: Noceti - first_name: Lorenzo full_name: Rosasco, Lorenzo last_name: Rosasco - first_name: Kun full_name: Zhang, Kun last_name: Zhang - first_name: Francesco full_name: Locatello, Francesco id: 26cfd52f-2483-11ee-8040-88983bcc06d4 last_name: Locatello orcid: 0000-0002-4850-0683 citation: ama: 'Montagna F, Noceti N, Rosasco L, Zhang K, Locatello F. Causal discovery with score matching on additive models with arbitrary noise. In: 2nd Conference on Causal Learning and Reasoning. ; 2023.' apa: Montagna, F., Noceti, N., Rosasco, L., Zhang, K., & Locatello, F. (2023). Causal discovery with score matching on additive models with arbitrary noise. In 2nd Conference on Causal Learning and Reasoning. Tübingen, Germany. chicago: Montagna, Francesco, Nicoletta Noceti, Lorenzo Rosasco, Kun Zhang, and Francesco Locatello. “Causal Discovery with Score Matching on Additive Models with Arbitrary Noise.” In 2nd Conference on Causal Learning and Reasoning, 2023. ieee: F. Montagna, N. Noceti, L. Rosasco, K. Zhang, and F. Locatello, “Causal discovery with score matching on additive models with arbitrary noise,” in 2nd Conference on Causal Learning and Reasoning, Tübingen, Germany, 2023. ista: 'Montagna F, Noceti N, Rosasco L, Zhang K, Locatello F. 2023. Causal discovery with score matching on additive models with arbitrary noise. 2nd Conference on Causal Learning and Reasoning. CLeaR: Conference on Causal Learning and Reasoning.' mla: Montagna, Francesco, et al. “Causal Discovery with Score Matching on Additive Models with Arbitrary Noise.” 2nd Conference on Causal Learning and Reasoning, 2023. short: F. Montagna, N. Noceti, L. Rosasco, K. Zhang, F. Locatello, in:, 2nd Conference on Causal Learning and Reasoning, 2023. conference: end_date: 2023-04-14 location: Tübingen, Germany name: 'CLeaR: Conference on Causal Learning and Reasoning' start_date: 2023-04-11 date_created: 2023-08-22T14:19:21Z date_published: 2023-04-01T00:00:00Z date_updated: 2023-09-13T09:00:31Z day: '01' department: - _id: FrLo extern: '1' external_id: arxiv: - '2304.03265' language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/2304.03265 month: '04' oa: 1 oa_version: Preprint publication: 2nd Conference on Causal Learning and Reasoning publication_status: published quality_controlled: '1' scopus_import: '1' status: public title: Causal discovery with score matching on additive models with arbitrary noise type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2023' ... --- _id: '14212' abstract: - lang: eng text: This paper demonstrates how to discover the whole causal graph from the second derivative of the log-likelihood in observational non-linear additive Gaussian noise models. Leveraging scalable machine learning approaches to approximate the score function ∇logp(X), we extend the work of Rolland et al. (2022) that only recovers the topological order from the score and requires an expensive pruning step removing spurious edges among those admitted by the ordering. Our analysis leads to DAS (acronym for Discovery At Scale), a practical algorithm that reduces the complexity of the pruning by a factor proportional to the graph size. In practice, DAS achieves competitive accuracy with current state-of-the-art while being over an order of magnitude faster. Overall, our approach enables principled and scalable causal discovery, significantly lowering the compute bar. article_processing_charge: No arxiv: 1 author: - first_name: Francesco full_name: Montagna, Francesco last_name: Montagna - first_name: Nicoletta full_name: Noceti, Nicoletta last_name: Noceti - first_name: Lorenzo full_name: Rosasco, Lorenzo last_name: Rosasco - first_name: Kun full_name: Zhang, Kun last_name: Zhang - first_name: Francesco full_name: Locatello, Francesco id: 26cfd52f-2483-11ee-8040-88983bcc06d4 last_name: Locatello orcid: 0000-0002-4850-0683 citation: ama: 'Montagna F, Noceti N, Rosasco L, Zhang K, Locatello F. Scalable causal discovery with score matching. In: 2nd Conference on Causal Learning and Reasoning. ; 2023.' apa: Montagna, F., Noceti, N., Rosasco, L., Zhang, K., & Locatello, F. (2023). Scalable causal discovery with score matching. In 2nd Conference on Causal Learning and Reasoning. Tübingen, Germany. chicago: Montagna, Francesco, Nicoletta Noceti, Lorenzo Rosasco, Kun Zhang, and Francesco Locatello. “Scalable Causal Discovery with Score Matching.” In 2nd Conference on Causal Learning and Reasoning, 2023. ieee: F. Montagna, N. Noceti, L. Rosasco, K. Zhang, and F. Locatello, “Scalable causal discovery with score matching,” in 2nd Conference on Causal Learning and Reasoning, Tübingen, Germany, 2023. ista: 'Montagna F, Noceti N, Rosasco L, Zhang K, Locatello F. 2023. Scalable causal discovery with score matching. 2nd Conference on Causal Learning and Reasoning. CLeaR: Conference on Causal Learning and Reasoning.' mla: Montagna, Francesco, et al. “Scalable Causal Discovery with Score Matching.” 2nd Conference on Causal Learning and Reasoning, 2023. short: F. Montagna, N. Noceti, L. Rosasco, K. Zhang, F. Locatello, in:, 2nd Conference on Causal Learning and Reasoning, 2023. conference: end_date: 2023-04-14 location: Tübingen, Germany name: 'CLeaR: Conference on Causal Learning and Reasoning' start_date: 2023-04-11 date_created: 2023-08-22T14:19:40Z date_published: 2023-04-01T00:00:00Z date_updated: 2023-09-13T09:03:24Z day: '01' department: - _id: FrLo extern: '1' external_id: arxiv: - '2304.03382' language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/2304.03382 month: '04' oa: 1 oa_version: Preprint publication: 2nd Conference on Causal Learning and Reasoning publication_status: published quality_controlled: '1' scopus_import: '1' status: public title: Scalable causal discovery with score matching type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2023' ... --- _id: '14214' abstract: - lang: eng text: 'Recent years have seen a surge of interest in learning high-level causal representations from low-level image pairs under interventions. Yet, existing efforts are largely limited to simple synthetic settings that are far away from real-world problems. In this paper, we present Causal Triplet, a causal representation learning benchmark featuring not only visually more complex scenes, but also two crucial desiderata commonly overlooked in previous works: (i) an actionable counterfactual setting, where only certain object-level variables allow for counterfactual observations whereas others do not; (ii) an interventional downstream task with an emphasis on out-of-distribution robustness from the independent causal mechanisms principle. Through extensive experiments, we find that models built with the knowledge of disentangled or object-centric representations significantly outperform their distributed counterparts. However, recent causal representation learning methods still struggle to identify such latent structures, indicating substantial challenges and opportunities for future work.' article_processing_charge: No arxiv: 1 author: - first_name: Yuejiang full_name: Liu, Yuejiang last_name: Liu - first_name: Alexandre full_name: Alahi, Alexandre last_name: Alahi - first_name: Chris full_name: Russell, Chris last_name: Russell - first_name: Max full_name: Horn, Max last_name: Horn - first_name: Dominik full_name: Zietlow, Dominik last_name: Zietlow - first_name: Bernhard full_name: Schölkopf, Bernhard last_name: Schölkopf - first_name: Francesco full_name: Locatello, Francesco id: 26cfd52f-2483-11ee-8040-88983bcc06d4 last_name: Locatello orcid: 0000-0002-4850-0683 citation: ama: 'Liu Y, Alahi A, Russell C, et al. Causal triplet: An open challenge for intervention-centric causal representation learning. In: 2nd Conference on Causal Learning and Reasoning. ; 2023.' apa: 'Liu, Y., Alahi, A., Russell, C., Horn, M., Zietlow, D., Schölkopf, B., & Locatello, F. (2023). Causal triplet: An open challenge for intervention-centric causal representation learning. In 2nd Conference on Causal Learning and Reasoning. Tübingen, Germany.' chicago: 'Liu, Yuejiang, Alexandre Alahi, Chris Russell, Max Horn, Dominik Zietlow, Bernhard Schölkopf, and Francesco Locatello. “Causal Triplet: An Open Challenge for Intervention-Centric Causal Representation Learning.” In 2nd Conference on Causal Learning and Reasoning, 2023.' ieee: 'Y. Liu et al., “Causal triplet: An open challenge for intervention-centric causal representation learning,” in 2nd Conference on Causal Learning and Reasoning, Tübingen, Germany, 2023.' ista: 'Liu Y, Alahi A, Russell C, Horn M, Zietlow D, Schölkopf B, Locatello F. 2023. Causal triplet: An open challenge for intervention-centric causal representation learning. 2nd Conference on Causal Learning and Reasoning. CLeaR: Conference on Causal Learning and Reasoning.' mla: 'Liu, Yuejiang, et al. “Causal Triplet: An Open Challenge for Intervention-Centric Causal Representation Learning.” 2nd Conference on Causal Learning and Reasoning, 2023.' short: Y. Liu, A. Alahi, C. Russell, M. Horn, D. Zietlow, B. Schölkopf, F. Locatello, in:, 2nd Conference on Causal Learning and Reasoning, 2023. conference: end_date: 2023-04-14 location: Tübingen, Germany name: 'CLeaR: Conference on Causal Learning and Reasoning' start_date: 2023-04-11 date_created: 2023-08-22T14:20:18Z date_published: 2023-04-12T00:00:00Z date_updated: 2023-09-13T09:23:08Z day: '12' department: - _id: FrLo extern: '1' external_id: arxiv: - '2301.05169' language: - iso: eng main_file_link: - open_access: '1' url: https://doi.org/10.48550/arXiv.2301.05169 month: '04' oa: 1 oa_version: Preprint publication: 2nd Conference on Causal Learning and Reasoning publication_status: published quality_controlled: '1' status: public title: 'Causal triplet: An open challenge for intervention-centric causal representation learning' type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2023' ... --- _id: '14217' abstract: - lang: eng text: 'Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space into latent representations. Ideally, the distribution of the data points in the latent space should depend only on the task, the data, the loss, and other architecture-specific constraints. However, factors such as the random weights initialization, training hyperparameters, or other sources of randomness in the training phase may induce incoherent latent spaces that hinder any form of reuse. Nevertheless, we empirically observe that, under the same data and modeling choices, the angles between the encodings within distinct latent spaces do not change. In this work, we propose the latent similarity between each sample and a fixed set of anchors as an alternative data representation, demonstrating that it can enforce the desired invariances without any additional training. We show how neural architectures can leverage these relative representations to guarantee, in practice, invariance to latent isometries and rescalings, effectively enabling latent space communication: from zero-shot model stitching to latent space comparison between diverse settings. We extensively validate the generalization capability of our approach on different datasets, spanning various modalities (images, text, graphs), tasks (e.g., classification, reconstruction) and architectures (e.g., CNNs, GCNs, transformers).' article_processing_charge: No arxiv: 1 author: - first_name: Luca full_name: Moschella, Luca last_name: Moschella - first_name: Valentino full_name: Maiorca, Valentino last_name: Maiorca - first_name: Marco full_name: Fumero, Marco last_name: Fumero - first_name: Antonio full_name: Norelli, Antonio last_name: Norelli - first_name: Francesco full_name: Locatello, Francesco id: 26cfd52f-2483-11ee-8040-88983bcc06d4 last_name: Locatello orcid: 0000-0002-4850-0683 - first_name: Emanuele full_name: Rodolà, Emanuele last_name: Rodolà citation: ama: 'Moschella L, Maiorca V, Fumero M, Norelli A, Locatello F, Rodolà E. Relative representations enable zero-shot latent space communication. In: The 11th International Conference on Learning Representations. ; 2023.' apa: Moschella, L., Maiorca, V., Fumero, M., Norelli, A., Locatello, F., & Rodolà, E. (2023). Relative representations enable zero-shot latent space communication. In The 11th International Conference on Learning Representations. Kigali, Rwanda. chicago: Moschella, Luca, Valentino Maiorca, Marco Fumero, Antonio Norelli, Francesco Locatello, and Emanuele Rodolà. “Relative Representations Enable Zero-Shot Latent Space Communication.” In The 11th International Conference on Learning Representations, 2023. ieee: L. Moschella, V. Maiorca, M. Fumero, A. Norelli, F. Locatello, and E. Rodolà, “Relative representations enable zero-shot latent space communication,” in The 11th International Conference on Learning Representations, Kigali, Rwanda, 2023. ista: Moschella L, Maiorca V, Fumero M, Norelli A, Locatello F, Rodolà E. 2023. Relative representations enable zero-shot latent space communication. The 11th International Conference on Learning Representations. International Conference on Machine Learning Representations. mla: Moschella, Luca, et al. “Relative Representations Enable Zero-Shot Latent Space Communication.” The 11th International Conference on Learning Representations, 2023. short: L. Moschella, V. Maiorca, M. Fumero, A. Norelli, F. Locatello, E. Rodolà, in:, The 11th International Conference on Learning Representations, 2023. conference: end_date: 2023-05-05 location: Kigali, Rwanda name: International Conference on Machine Learning Representations start_date: 2023-05-01 date_created: 2023-08-22T14:22:20Z date_published: 2023-05-01T00:00:00Z date_updated: 2023-09-13T09:44:26Z day: '01' department: - _id: FrLo extern: '1' external_id: arxiv: - '2209.15430' language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/2209.15430 month: '05' oa: 1 oa_version: Preprint publication: The 11th International Conference on Learning Representations publication_status: published quality_controlled: '1' status: public title: Relative representations enable zero-shot latent space communication type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2023' ... --- _id: '14218' abstract: - lang: eng text: Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition in an unsupervised way has become an important line of research. However, current methods are restricted to simulated data or require additional information in the form of motion or depth in order to successfully discover objects. In this work, we overcome this limitation by showing that reconstructing features from models trained in a self-supervised manner is a sufficient training signal for object-centric representations to arise in a fully unsupervised way. Our approach, DINOSAUR, significantly out-performs existing image-based object-centric learning models on simulated data and is the first unsupervised object-centric model that scales to real-world datasets such as COCO and PASCAL VOC. DINOSAUR is conceptually simple and shows competitive performance compared to more involved pipelines from the computer vision literature. article_processing_charge: No arxiv: 1 author: - first_name: Maximilian full_name: Seitzer, Maximilian last_name: Seitzer - first_name: Max full_name: Horn, Max last_name: Horn - first_name: Andrii full_name: Zadaianchuk, Andrii last_name: Zadaianchuk - first_name: Dominik full_name: Zietlow, Dominik last_name: Zietlow - first_name: Tianjun full_name: Xiao, Tianjun last_name: Xiao - first_name: Carl-Johann Simon-Gabriel full_name: Carl-Johann Simon-Gabriel, Carl-Johann Simon-Gabriel last_name: Carl-Johann Simon-Gabriel - first_name: Tong full_name: He, Tong last_name: He - first_name: Zheng full_name: Zhang, Zheng last_name: Zhang - first_name: Bernhard full_name: Schölkopf, Bernhard last_name: Schölkopf - first_name: Thomas full_name: Brox, Thomas last_name: Brox - first_name: Francesco full_name: Locatello, Francesco id: 26cfd52f-2483-11ee-8040-88983bcc06d4 last_name: Locatello orcid: 0000-0002-4850-0683 citation: ama: 'Seitzer M, Horn M, Zadaianchuk A, et al. Bridging the gap to real-world object-centric learning. In: The 11th International Conference on Learning Representations. ; 2023.' apa: Seitzer, M., Horn, M., Zadaianchuk, A., Zietlow, D., Xiao, T., Carl-Johann Simon-Gabriel, C.-J. S.-G., … Locatello, F. (2023). Bridging the gap to real-world object-centric learning. In The 11th International Conference on Learning Representations. Kigali, Rwanda. chicago: Seitzer, Maximilian, Max Horn, Andrii Zadaianchuk, Dominik Zietlow, Tianjun Xiao, Carl-Johann Simon-Gabriel Carl-Johann Simon-Gabriel, Tong He, et al. “Bridging the Gap to Real-World Object-Centric Learning.” In The 11th International Conference on Learning Representations, 2023. ieee: M. Seitzer et al., “Bridging the gap to real-world object-centric learning,” in The 11th International Conference on Learning Representations, Kigali, Rwanda, 2023. ista: 'Seitzer M, Horn M, Zadaianchuk A, Zietlow D, Xiao T, Carl-Johann Simon-Gabriel C-JS-G, He T, Zhang Z, Schölkopf B, Brox T, Locatello F. 2023. Bridging the gap to real-world object-centric learning. The 11th International Conference on Learning Representations. ICLR: International Conference on Learning Representations.' mla: Seitzer, Maximilian, et al. “Bridging the Gap to Real-World Object-Centric Learning.” The 11th International Conference on Learning Representations, 2023. short: M. Seitzer, M. Horn, A. Zadaianchuk, D. Zietlow, T. Xiao, C.-J.S.-G. Carl-Johann Simon-Gabriel, T. He, Z. Zhang, B. Schölkopf, T. Brox, F. Locatello, in:, The 11th International Conference on Learning Representations, 2023. conference: end_date: 2023-05-05 location: Kigali, Rwanda name: 'ICLR: International Conference on Learning Representations' start_date: 2023-05-01 date_created: 2023-08-22T14:22:41Z date_published: 2023-05-10T00:00:00Z date_updated: 2023-09-13T11:37:03Z day: '10' department: - _id: FrLo extern: '1' external_id: arxiv: - '2209.14860' language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/2209.14860 month: '05' oa: 1 oa_version: Preprint publication: The 11th International Conference on Learning Representations publication_status: published quality_controlled: '1' status: public title: Bridging the gap to real-world object-centric learning type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2023' ... --- _id: '14219' abstract: - lang: eng text: "In this paper, we show that recent advances in self-supervised feature\r\nlearning enable unsupervised object discovery and semantic segmentation with a\r\nperformance that matches the state of the field on supervised semantic\r\nsegmentation 10 years ago. We propose a methodology based on unsupervised\r\nsaliency masks and self-supervised feature clustering to kickstart object\r\ndiscovery followed by training a semantic segmentation network on pseudo-labels\r\nto bootstrap the system on images with multiple objects. We present results on\r\nPASCAL VOC that go far beyond the current state of the art (50.0 mIoU), and we\r\nreport for the first time results on MS COCO for the whole set of 81 classes:\r\nour method discovers 34 categories with more than $20\\%$ IoU, while obtaining\r\nan average IoU of 19.6 for all 81 categories." article_processing_charge: No arxiv: 1 author: - first_name: Andrii full_name: Zadaianchuk, Andrii last_name: Zadaianchuk - first_name: Matthaeus full_name: Kleindessner, Matthaeus last_name: Kleindessner - first_name: Yi full_name: Zhu, Yi last_name: Zhu - first_name: Francesco full_name: Locatello, Francesco id: 26cfd52f-2483-11ee-8040-88983bcc06d4 last_name: Locatello orcid: 0000-0002-4850-0683 - first_name: Thomas full_name: Brox, Thomas last_name: Brox citation: ama: 'Zadaianchuk A, Kleindessner M, Zhu Y, Locatello F, Brox T. Unsupervised semantic segmentation with self-supervised object-centric representations. In: The 11th International Conference on Learning Representations. ; 2023.' apa: Zadaianchuk, A., Kleindessner, M., Zhu, Y., Locatello, F., & Brox, T. (2023). Unsupervised semantic segmentation with self-supervised object-centric representations. In The 11th International Conference on Learning Representations. Kigali, Rwanda. chicago: Zadaianchuk, Andrii, Matthaeus Kleindessner, Yi Zhu, Francesco Locatello, and Thomas Brox. “Unsupervised Semantic Segmentation with Self-Supervised Object-Centric Representations.” In The 11th International Conference on Learning Representations, 2023. ieee: A. Zadaianchuk, M. Kleindessner, Y. Zhu, F. Locatello, and T. Brox, “Unsupervised semantic segmentation with self-supervised object-centric representations,” in The 11th International Conference on Learning Representations, Kigali, Rwanda, 2023. ista: 'Zadaianchuk A, Kleindessner M, Zhu Y, Locatello F, Brox T. 2023. Unsupervised semantic segmentation with self-supervised object-centric representations. The 11th International Conference on Learning Representations. ICLR: International Conference on Learning Representations.' mla: Zadaianchuk, Andrii, et al. “Unsupervised Semantic Segmentation with Self-Supervised Object-Centric Representations.” The 11th International Conference on Learning Representations, 2023. short: A. Zadaianchuk, M. Kleindessner, Y. Zhu, F. Locatello, T. Brox, in:, The 11th International Conference on Learning Representations, 2023. conference: end_date: 2023-05-05 location: Kigali, Rwanda name: 'ICLR: International Conference on Learning Representations' start_date: 2023-05-01 date_created: 2023-08-22T14:22:58Z date_published: 2023-05-01T00:00:00Z date_updated: 2023-09-13T11:25:43Z day: '01' department: - _id: FrLo extern: '1' external_id: arxiv: - '2207.05027' language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/2207.05027 month: '05' oa: 1 oa_version: Preprint publication: The 11th International Conference on Learning Representations publication_status: published quality_controlled: '1' status: public title: Unsupervised semantic segmentation with self-supervised object-centric representations type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2023' ... --- _id: '14222' abstract: - lang: eng text: Learning generative object models from unlabelled videos is a long standing problem and required for causal scene modeling. We decompose this problem into three easier subtasks, and provide candidate solutions for each of them. Inspired by the Common Fate Principle of Gestalt Psychology, we first extract (noisy) masks of moving objects via unsupervised motion segmentation. Second, generative models are trained on the masks of the background and the moving objects, respectively. Third, background and foreground models are combined in a conditional "dead leaves" scene model to sample novel scene configurations where occlusions and depth layering arise naturally. To evaluate the individual stages, we introduce the Fishbowl dataset positioned between complex real-world scenes and common object-centric benchmarks of simplistic objects. We show that our approach allows learning generative models that generalize beyond the occlusions present in the input videos, and represent scenes in a modular fashion that allows sampling plausible scenes outside the training distribution by permitting, for instance, object numbers or densities not observed in the training set. article_number: '2110.06562' article_processing_charge: No arxiv: 1 author: - first_name: Matthias full_name: Tangemann, Matthias last_name: Tangemann - first_name: Steffen full_name: Schneider, Steffen last_name: Schneider - first_name: Julius von full_name: Kügelgen, Julius von last_name: Kügelgen - first_name: Francesco full_name: Locatello, Francesco id: 26cfd52f-2483-11ee-8040-88983bcc06d4 last_name: Locatello orcid: 0000-0002-4850-0683 - first_name: Peter full_name: Gehler, Peter last_name: Gehler - first_name: Thomas full_name: Brox, Thomas last_name: Brox - first_name: Matthias full_name: Kümmerer, Matthias last_name: Kümmerer - first_name: Matthias full_name: Bethge, Matthias last_name: Bethge - first_name: Bernhard full_name: Schölkopf, Bernhard last_name: Schölkopf citation: ama: 'Tangemann M, Schneider S, Kügelgen J von, et al. Unsupervised object learning via common fate. In: 2nd Conference on Causal Learning and Reasoning. ; 2023.' apa: Tangemann, M., Schneider, S., Kügelgen, J. von, Locatello, F., Gehler, P., Brox, T., … Schölkopf, B. (2023). Unsupervised object learning via common fate. In 2nd Conference on Causal Learning and Reasoning. Tübingen, Germany. chicago: Tangemann, Matthias, Steffen Schneider, Julius von Kügelgen, Francesco Locatello, Peter Gehler, Thomas Brox, Matthias Kümmerer, Matthias Bethge, and Bernhard Schölkopf. “Unsupervised Object Learning via Common Fate.” In 2nd Conference on Causal Learning and Reasoning, 2023. ieee: M. Tangemann et al., “Unsupervised object learning via common fate,” in 2nd Conference on Causal Learning and Reasoning, Tübingen, Germany, 2023. ista: 'Tangemann M, Schneider S, Kügelgen J von, Locatello F, Gehler P, Brox T, Kümmerer M, Bethge M, Schölkopf B. 2023. Unsupervised object learning via common fate. 2nd Conference on Causal Learning and Reasoning. CLeaR: Conference on Causal Learning and Reasoning, 2110.06562.' mla: Tangemann, Matthias, et al. “Unsupervised Object Learning via Common Fate.” 2nd Conference on Causal Learning and Reasoning, 2110.06562, 2023. short: M. Tangemann, S. Schneider, J. von Kügelgen, F. Locatello, P. Gehler, T. Brox, M. Kümmerer, M. Bethge, B. Schölkopf, in:, 2nd Conference on Causal Learning and Reasoning, 2023. conference: end_date: 2023-04-14 location: Tübingen, Germany name: 'CLeaR: Conference on Causal Learning and Reasoning' start_date: 2023-04-11 date_created: 2023-08-22T14:23:54Z date_published: 2023-04-15T00:00:00Z date_updated: 2023-09-13T11:31:14Z day: '15' department: - _id: FrLo extern: '1' external_id: arxiv: - '2110.06562' language: - iso: eng main_file_link: - open_access: '1' url: https://arxiv.org/abs/2110.06562 month: '04' oa: 1 oa_version: Preprint publication: 2nd Conference on Causal Learning and Reasoning publication_status: published quality_controlled: '1' status: public title: Unsupervised object learning via common fate type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2023' ... --- _id: '14226' abstract: - lang: eng text: "We introduce the notion of a Faustian interchange in a 1-parameter family of smooth\r\nfunctions to generalize the medial axis to critical points of index larger than 0.\r\nWe construct and implement a general purpose algorithm for approximating such\r\ngeneralized medial axes." alternative_title: - ISTA Master's Thesis article_processing_charge: No author: - first_name: Elizabeth R full_name: Stephenson, Elizabeth R id: 2D04F932-F248-11E8-B48F-1D18A9856A87 last_name: Stephenson orcid: 0000-0002-6862-208X citation: ama: Stephenson ER. Generalizing medial axes with homology switches. 2023. doi:10.15479/at:ista:14226 apa: Stephenson, E. R. (2023). Generalizing medial axes with homology switches. Institute of Science and Technology Austria. https://doi.org/10.15479/at:ista:14226 chicago: Stephenson, Elizabeth R. “Generalizing Medial Axes with Homology Switches.” Institute of Science and Technology Austria, 2023. https://doi.org/10.15479/at:ista:14226. ieee: E. R. Stephenson, “Generalizing medial axes with homology switches,” Institute of Science and Technology Austria, 2023. ista: Stephenson ER. 2023. Generalizing medial axes with homology switches. Institute of Science and Technology Austria. mla: Stephenson, Elizabeth R. Generalizing Medial Axes with Homology Switches. Institute of Science and Technology Austria, 2023, doi:10.15479/at:ista:14226. short: E.R. Stephenson, Generalizing Medial Axes with Homology Switches, Institute of Science and Technology Austria, 2023. date_created: 2023-08-24T13:01:18Z date_published: 2023-08-24T00:00:00Z date_updated: 2024-02-26T23:30:04Z day: '24' ddc: - '500' degree_awarded: MS department: - _id: GradSch - _id: HeEd doi: 10.15479/at:ista:14226 file: - access_level: closed checksum: 453caf851d75c3478c10ed09bd242a91 content_type: application/x-zip-compressed creator: cchlebak date_created: 2023-08-24T13:02:49Z date_updated: 2024-02-26T23:30:03Z embargo_to: open_access file_id: '14227' file_name: documents-export-2023-08-24.zip file_size: 15501411 relation: source_file - access_level: open_access checksum: 7349d29963d6695e555e171748648d9a content_type: application/pdf creator: cchlebak date_created: 2023-08-24T13:03:42Z date_updated: 2024-02-26T23:30:03Z embargo: 2024-02-25 file_id: '14228' file_name: thesis_pdf_a.pdf file_size: 6854783 relation: main_file file_date_updated: 2024-02-26T23:30:03Z has_accepted_license: '1' language: - iso: eng month: '08' oa: 1 oa_version: Published Version page: '43' publication_identifier: issn: - 2791-4585 publication_status: published publisher: Institute of Science and Technology Austria status: public supervisor: - first_name: Herbert full_name: Edelsbrunner, Herbert id: 3FB178DA-F248-11E8-B48F-1D18A9856A87 last_name: Edelsbrunner orcid: 0000-0002-9823-6833 title: Generalizing medial axes with homology switches type: dissertation user_id: 8b945eb4-e2f2-11eb-945a-df72226e66a9 year: '2023' ... --- _id: '14238' abstract: - lang: eng text: We demonstrate that a sodium dimer, Na2(13Σ+u), residing on the surface of a helium nanodroplet, can be set into rotation by a nonresonant 1.0 ps infrared laser pulse. The time-dependent degree of alignment measured, exhibits a periodic, gradually decreasing structure that deviates qualitatively from that expected for gas-phase dimers. Comparison to alignment dynamics calculated from the time-dependent rotational Schrödinger equation shows that the deviation is due to the alignment dependent interaction between the dimer and the droplet surface. This interaction confines the dimer to the tangential plane of the droplet surface at the point where it resides and is the reason that the observed alignment dynamics is also well described by a 2D quantum rotor model. acknowledgement: H. S. acknowledges support from The Villum Foundation through a Villum Investigator Grant No. 25886. M. L. acknowledges support by the European Research Council (ERC) Starting Grant No. 801770 (ANGULON). F. J. and R. E. Z. acknowledge support from the Centre for Scientific Computing, Aarhus and the JKU scientific computing administration, Linz, respectively. article_number: '053201' article_processing_charge: No article_type: original arxiv: 1 author: - first_name: Lorenz full_name: Kranabetter, Lorenz last_name: Kranabetter - first_name: Henrik H. full_name: Kristensen, Henrik H. last_name: Kristensen - first_name: Areg full_name: Ghazaryan, Areg id: 4AF46FD6-F248-11E8-B48F-1D18A9856A87 last_name: Ghazaryan orcid: 0000-0001-9666-3543 - first_name: Constant A. full_name: Schouder, Constant A. last_name: Schouder - first_name: Adam S. full_name: Chatterley, Adam S. last_name: Chatterley - first_name: Paul full_name: Janssen, Paul last_name: Janssen - first_name: Frank full_name: Jensen, Frank last_name: Jensen - first_name: Robert E. full_name: Zillich, Robert E. last_name: Zillich - first_name: Mikhail full_name: Lemeshko, Mikhail id: 37CB05FA-F248-11E8-B48F-1D18A9856A87 last_name: Lemeshko orcid: 0000-0002-6990-7802 - first_name: Henrik full_name: Stapelfeldt, Henrik last_name: Stapelfeldt citation: ama: Kranabetter L, Kristensen HH, Ghazaryan A, et al. Nonadiabatic laser-induced alignment dynamics of molecules on a surface. Physical Review Letters. 2023;131(5). doi:10.1103/PhysRevLett.131.053201 apa: Kranabetter, L., Kristensen, H. H., Ghazaryan, A., Schouder, C. A., Chatterley, A. S., Janssen, P., … Stapelfeldt, H. (2023). Nonadiabatic laser-induced alignment dynamics of molecules on a surface. Physical Review Letters. American Physical Society. https://doi.org/10.1103/PhysRevLett.131.053201 chicago: Kranabetter, Lorenz, Henrik H. Kristensen, Areg Ghazaryan, Constant A. Schouder, Adam S. Chatterley, Paul Janssen, Frank Jensen, Robert E. Zillich, Mikhail Lemeshko, and Henrik Stapelfeldt. “Nonadiabatic Laser-Induced Alignment Dynamics of Molecules on a Surface.” Physical Review Letters. American Physical Society, 2023. https://doi.org/10.1103/PhysRevLett.131.053201. ieee: L. Kranabetter et al., “Nonadiabatic laser-induced alignment dynamics of molecules on a surface,” Physical Review Letters, vol. 131, no. 5. American Physical Society, 2023. ista: Kranabetter L, Kristensen HH, Ghazaryan A, Schouder CA, Chatterley AS, Janssen P, Jensen F, Zillich RE, Lemeshko M, Stapelfeldt H. 2023. Nonadiabatic laser-induced alignment dynamics of molecules on a surface. Physical Review Letters. 131(5), 053201. mla: Kranabetter, Lorenz, et al. “Nonadiabatic Laser-Induced Alignment Dynamics of Molecules on a Surface.” Physical Review Letters, vol. 131, no. 5, 053201, American Physical Society, 2023, doi:10.1103/PhysRevLett.131.053201. short: L. Kranabetter, H.H. Kristensen, A. Ghazaryan, C.A. Schouder, A.S. Chatterley, P. Janssen, F. Jensen, R.E. Zillich, M. Lemeshko, H. Stapelfeldt, Physical Review Letters 131 (2023). date_created: 2023-08-27T22:01:16Z date_published: 2023-08-04T00:00:00Z date_updated: 2023-12-13T12:18:54Z day: '04' department: - _id: MiLe doi: 10.1103/PhysRevLett.131.053201 ec_funded: 1 external_id: arxiv: - '2308.15247' isi: - '001101784100001' pmid: - '37595218' intvolume: ' 131' isi: 1 issue: '5' language: - iso: eng main_file_link: - open_access: '1' url: https://doi.org/10.48550/arXiv.2308.15247 month: '08' oa: 1 oa_version: Preprint pmid: 1 project: - _id: 2688CF98-B435-11E9-9278-68D0E5697425 call_identifier: H2020 grant_number: '801770' name: 'Angulon: physics and applications of a new quasiparticle' publication: Physical Review Letters publication_identifier: eissn: - 1079-7114 issn: - 0031-9007 publication_status: published publisher: American Physical Society quality_controlled: '1' scopus_import: '1' status: public title: Nonadiabatic laser-induced alignment dynamics of molecules on a surface type: journal_article user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 volume: 131 year: '2023' ... --- _id: '14239' abstract: - lang: eng text: "Given a resolution of rational singularities π:X~→X over a field of characteristic zero, we use a Hodge-theoretic argument to prove that the image of the functor \ Rπ∗:Db(X~)→Db(X)\r\n between bounded derived categories of coherent sheaves generates Db(X)\r\n as a triangulated category. This gives a weak version of the Bondal–Orlov localization conjecture [BO02], answering a question from [PS21]. The same result is established more generally for proper (not necessarily birational) morphisms π:X~→X , with X~\r\n smooth, satisfying Rπ∗(OX~)=OX ." acknowledgement: "We thank Agnieszka Bodzenta-Skibińska, Paolo Cascini, Wahei Hara, Sándor Kovács, Alexander Kuznetsov, Mircea Musta ă, Nebojsa Pavic, Pavel Sechin, and Michael Wemyss for discussions and e-mail correspondence. We also thank the anonymous referee for the helpful comments. M.M. was supported by the Institute of Science and Technology Austria. This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement no. 101034413. E.S. was partially supported by the EPSRC grant EP/T019379/1 “Derived categories and algebraic K-theory of singularities”, and by the ERC Synergy grant “Modern Aspects of Geometry: Categories, Cycles and Cohomology of Hyperkähler Varieties.”\r\n\r\n" article_number: e66 article_processing_charge: Yes article_type: original arxiv: 1 author: - first_name: Mirko full_name: Mauri, Mirko id: 2cf70c34-09c1-11ed-bd8d-c34fac206130 last_name: Mauri - first_name: Evgeny full_name: Shinder, Evgeny last_name: Shinder citation: ama: Mauri M, Shinder E. Homological Bondal-Orlov localization conjecture for rational singularities. Forum of Mathematics, Sigma. 2023;11. doi:10.1017/fms.2023.65 apa: Mauri, M., & Shinder, E. (2023). Homological Bondal-Orlov localization conjecture for rational singularities. Forum of Mathematics, Sigma. Cambridge University Press. https://doi.org/10.1017/fms.2023.65 chicago: Mauri, Mirko, and Evgeny Shinder. “Homological Bondal-Orlov Localization Conjecture for Rational Singularities.” Forum of Mathematics, Sigma. Cambridge University Press, 2023. https://doi.org/10.1017/fms.2023.65. ieee: M. Mauri and E. Shinder, “Homological Bondal-Orlov localization conjecture for rational singularities,” Forum of Mathematics, Sigma, vol. 11. Cambridge University Press, 2023. ista: Mauri M, Shinder E. 2023. Homological Bondal-Orlov localization conjecture for rational singularities. Forum of Mathematics, Sigma. 11, e66. mla: Mauri, Mirko, and Evgeny Shinder. “Homological Bondal-Orlov Localization Conjecture for Rational Singularities.” Forum of Mathematics, Sigma, vol. 11, e66, Cambridge University Press, 2023, doi:10.1017/fms.2023.65. short: M. Mauri, E. Shinder, Forum of Mathematics, Sigma 11 (2023). date_created: 2023-08-27T22:01:16Z date_published: 2023-08-03T00:00:00Z date_updated: 2023-12-13T12:18:18Z day: '03' ddc: - '510' department: - _id: TaHa doi: 10.1017/fms.2023.65 ec_funded: 1 external_id: arxiv: - '2212.06786' isi: - '001041926700001' file: - access_level: open_access checksum: c36241750cc5cb06890aec0ecdfee626 content_type: application/pdf creator: dernst date_created: 2023-09-05T06:43:11Z date_updated: 2023-09-05T06:43:11Z file_id: '14266' file_name: 2023_ForumMathematics_Mauri.pdf file_size: 280865 relation: main_file success: 1 file_date_updated: 2023-09-05T06:43:11Z has_accepted_license: '1' intvolume: ' 11' isi: 1 language: - iso: eng month: '08' oa: 1 oa_version: Published Version project: - _id: fc2ed2f7-9c52-11eb-aca3-c01059dda49c call_identifier: H2020 grant_number: '101034413' name: 'IST-BRIDGE: International postdoctoral program' publication: Forum of Mathematics, Sigma publication_identifier: eissn: - 2050-5094 publication_status: published publisher: Cambridge University Press quality_controlled: '1' scopus_import: '1' status: public title: Homological Bondal-Orlov localization conjecture for rational singularities tmp: image: /images/cc_by.png legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0) short: CC BY (4.0) type: journal_article user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 volume: 11 year: '2023' ... --- _id: '14240' abstract: - lang: eng text: This paper introduces a novel method for simulating large bodies of water as a height field. At the start of each time step, we partition the waves into a bulk flow (which approximately satisfies the assumptions of the shallow water equations) and surface waves (which approximately satisfy the assumptions of Airy wave theory). We then solve the two wave regimes separately using appropriate state-of-the-art techniques, and re-combine the resulting wave velocities at the end of each step. This strategy leads to the first heightfield wave model capable of simulating complex interactions between both deep and shallow water effects, like the waves from a boat wake sloshing up onto a beach, or a dam break producing wave interference patterns and eddies. We also analyze the numerical dispersion created by our method and derive an exact correction factor for waves at a constant water depth, giving us a numerically perfect re-creation of theoretical water wave dispersion patterns. acknowledged_ssus: - _id: ScienComp acknowledgement: "We thank Georg Sperl for helping with early research for this paper, Mickael Ly and Yi-Lu Chen for proofreading, and members of the ISTA Visual Computing Group for general feedback. This project was funded in part by the European Research Council (ERC Consolidator Grant 101045083 CoDiNA).\r\nThe motorboat and sailboat were modeled by Sergei and the palmtrees by YadroGames. The environment map was created by Emil Persson." article_number: '83' article_processing_charge: Yes (in subscription journal) article_type: original author: - first_name: Stefan full_name: Jeschke, Stefan id: 44D6411A-F248-11E8-B48F-1D18A9856A87 last_name: Jeschke - first_name: Christopher J full_name: Wojtan, Christopher J id: 3C61F1D2-F248-11E8-B48F-1D18A9856A87 last_name: Wojtan orcid: 0000-0001-6646-5546 citation: ama: Jeschke S, Wojtan C. Generalizing shallow water simulations with dispersive surface waves. ACM Transactions on Graphics. 2023;42(4). doi:10.1145/3592098 apa: Jeschke, S., & Wojtan, C. (2023). Generalizing shallow water simulations with dispersive surface waves. ACM Transactions on Graphics. Association for Computing Machinery. https://doi.org/10.1145/3592098 chicago: Jeschke, Stefan, and Chris Wojtan. “Generalizing Shallow Water Simulations with Dispersive Surface Waves.” ACM Transactions on Graphics. Association for Computing Machinery, 2023. https://doi.org/10.1145/3592098. ieee: S. Jeschke and C. Wojtan, “Generalizing shallow water simulations with dispersive surface waves,” ACM Transactions on Graphics, vol. 42, no. 4. Association for Computing Machinery, 2023. ista: Jeschke S, Wojtan C. 2023. Generalizing shallow water simulations with dispersive surface waves. ACM Transactions on Graphics. 42(4), 83. mla: Jeschke, Stefan, and Chris Wojtan. “Generalizing Shallow Water Simulations with Dispersive Surface Waves.” ACM Transactions on Graphics, vol. 42, no. 4, 83, Association for Computing Machinery, 2023, doi:10.1145/3592098. short: S. Jeschke, C. Wojtan, ACM Transactions on Graphics 42 (2023). date_created: 2023-08-27T22:01:17Z date_published: 2023-08-01T00:00:00Z date_updated: 2024-01-02T09:35:55Z day: '01' ddc: - '000' department: - _id: ChWo doi: 10.1145/3592098 external_id: isi: - '001044671300049' file: - access_level: open_access checksum: 1d178bb2f8011d9f5aedda6427e18c7a content_type: video/mp4 creator: sjeschke date_created: 2023-12-21T12:26:40Z date_updated: 2023-12-21T12:26:40Z file_id: '14704' file_name: PaperVideo_final.mp4 file_size: 511572575 relation: main_file success: 1 - access_level: open_access checksum: a49b2e744d5cd1276bb8b2e0ce6dc638 content_type: application/pdf creator: dernst date_created: 2024-01-02T09:34:27Z date_updated: 2024-01-02T09:34:27Z file_id: '14725' file_name: 2023_ACMToG_Jeschke.pdf file_size: 7469177 relation: main_file success: 1 file_date_updated: 2024-01-02T09:34:27Z has_accepted_license: '1' intvolume: ' 42' isi: 1 issue: '4' language: - iso: eng month: '08' oa: 1 oa_version: Published Version project: - _id: 34bc2376-11ca-11ed-8bc3-9a3b3961a088 grant_number: '101045083' name: Computational Discovery of Numerical Algorithms for Animation and Simulation of Natural Phenomena publication: ACM Transactions on Graphics publication_identifier: eissn: - 1557-7368 issn: - 0730-0301 publication_status: published publisher: Association for Computing Machinery quality_controlled: '1' scopus_import: '1' status: public title: Generalizing shallow water simulations with dispersive surface waves tmp: image: /images/cc_by.png legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0) short: CC BY (4.0) type: journal_article user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 volume: 42 year: '2023' ... --- _id: '14241' abstract: - lang: eng text: We present a technique to optimize the reflectivity of a surface while preserving its overall shape. The naïve optimization of the mesh vertices using the gradients of reflectivity simulations results in undesirable distortion. In contrast, our robust formulation optimizes the surface normal as an independent variable that bridges the reflectivity term with differential rendering, and the regularization term with as-rigid-as-possible elastic energy. We further adaptively subdivide the input mesh to improve the convergence. Consequently, our method can minimize the retroreflectivity of a wide range of input shapes, resulting in sharply creased shapes ubiquitous among stealth aircraft and Sci-Fi vehicles. Furthermore, by changing the reward for the direction of the outgoing light directions, our method can be applied to other reflectivity design tasks, such as the optimization of architectural walls to concentrate light in a specific region. We have tested the proposed method using light-transport simulations and real-world 3D-printed objects. acknowledgement: "The authors would like to thank Yuki Koyama and Takeo Igarashi for early discussions, and Yuta Yaguchi for support in 3D printing. This research is partially supported by the Israel Science Foundation grant number 1390/19.\r\n" article_number: '20' article_processing_charge: No arxiv: 1 author: - first_name: Kenji full_name: Tojo, Kenji last_name: Tojo - first_name: Ariel full_name: Shamir, Ariel last_name: Shamir - first_name: Bernd full_name: Bickel, Bernd id: 49876194-F248-11E8-B48F-1D18A9856A87 last_name: Bickel orcid: 0000-0001-6511-9385 - first_name: Nobuyuki full_name: Umetani, Nobuyuki last_name: Umetani citation: ama: 'Tojo K, Shamir A, Bickel B, Umetani N. Stealth shaper: Reflectivity optimization as surface stylization. In: SIGGRAPH 2023 Conference Proceedings. Association for Computing Machinery; 2023. doi:10.1145/3588432.3591542' apa: 'Tojo, K., Shamir, A., Bickel, B., & Umetani, N. (2023). Stealth shaper: Reflectivity optimization as surface stylization. In SIGGRAPH 2023 Conference Proceedings. Los Angeles, CA, United States: Association for Computing Machinery. https://doi.org/10.1145/3588432.3591542' chicago: 'Tojo, Kenji, Ariel Shamir, Bernd Bickel, and Nobuyuki Umetani. “Stealth Shaper: Reflectivity Optimization as Surface Stylization.” In SIGGRAPH 2023 Conference Proceedings. Association for Computing Machinery, 2023. https://doi.org/10.1145/3588432.3591542.' ieee: 'K. Tojo, A. Shamir, B. Bickel, and N. Umetani, “Stealth shaper: Reflectivity optimization as surface stylization,” in SIGGRAPH 2023 Conference Proceedings, Los Angeles, CA, United States, 2023.' ista: 'Tojo K, Shamir A, Bickel B, Umetani N. 2023. Stealth shaper: Reflectivity optimization as surface stylization. SIGGRAPH 2023 Conference Proceedings. SIGGRAPH: Computer Graphics and Interactive Techniques Conference, 20.' mla: 'Tojo, Kenji, et al. “Stealth Shaper: Reflectivity Optimization as Surface Stylization.” SIGGRAPH 2023 Conference Proceedings, 20, Association for Computing Machinery, 2023, doi:10.1145/3588432.3591542.' short: K. Tojo, A. Shamir, B. Bickel, N. Umetani, in:, SIGGRAPH 2023 Conference Proceedings, Association for Computing Machinery, 2023. conference: end_date: 2023-08-10 location: Los Angeles, CA, United States name: 'SIGGRAPH: Computer Graphics and Interactive Techniques Conference' start_date: 2023-08-06 date_created: 2023-08-27T22:01:17Z date_published: 2023-07-23T00:00:00Z date_updated: 2023-09-05T07:22:03Z day: '23' department: - _id: BeBi doi: 10.1145/3588432.3591542 external_id: arxiv: - '2305.05944' language: - iso: eng main_file_link: - open_access: '1' url: https://doi.org/10.48550/arXiv.2305.05944 month: '07' oa: 1 oa_version: Preprint publication: SIGGRAPH 2023 Conference Proceedings publication_identifier: isbn: - '9798400701597' publication_status: published publisher: Association for Computing Machinery quality_controlled: '1' scopus_import: '1' status: public title: 'Stealth shaper: Reflectivity optimization as surface stylization' type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 year: '2023' ... --- _id: '14242' abstract: - lang: eng text: We study the problem of training and certifying adversarially robust quantized neural networks (QNNs). Quantization is a technique for making neural networks more efficient by running them using low-bit integer arithmetic and is therefore commonly adopted in industry. Recent work has shown that floating-point neural networks that have been verified to be robust can become vulnerable to adversarial attacks after quantization, and certification of the quantized representation is necessary to guarantee robustness. In this work, we present quantization-aware interval bound propagation (QA-IBP), a novel method for training robust QNNs. Inspired by advances in robust learning of non-quantized networks, our training algorithm computes the gradient of an abstract representation of the actual network. Unlike existing approaches, our method can handle the discrete semantics of QNNs. Based on QA-IBP, we also develop a complete verification procedure for verifying the adversarial robustness of QNNs, which is guaranteed to terminate and produce a correct answer. Compared to existing approaches, the key advantage of our verification procedure is that it runs entirely on GPU or other accelerator devices. We demonstrate experimentally that our approach significantly outperforms existing methods and establish the new state-of-the-art for training and certifying the robustness of QNNs. acknowledgement: "This work was supported in part by the ERC-2020-AdG 101020093, ERC CoG 863818 (FoRM-SMArt) and the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie Grant Agreement No. 665385. Research was sponsored by the United\r\nStates Air Force Research Laboratory and the United States Air Force Artificial Intelligence Accelerator and was accomplished under Cooperative Agreement Number FA8750-19-2-\r\n1000. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied,\r\nof the United States Air Force or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright\r\nnotation herein. The research was also funded in part by the AI2050 program at Schmidt Futures (Grant G-22-63172) and Capgemini SE." article_processing_charge: No arxiv: 1 author: - first_name: Mathias full_name: Lechner, Mathias id: 3DC22916-F248-11E8-B48F-1D18A9856A87 last_name: Lechner - first_name: Dorde full_name: Zikelic, Dorde id: 294AA7A6-F248-11E8-B48F-1D18A9856A87 last_name: Zikelic orcid: 0000-0002-4681-1699 - first_name: Krishnendu full_name: Chatterjee, Krishnendu id: 2E5DCA20-F248-11E8-B48F-1D18A9856A87 last_name: Chatterjee orcid: 0000-0002-4561-241X - first_name: Thomas A full_name: Henzinger, Thomas A id: 40876CD8-F248-11E8-B48F-1D18A9856A87 last_name: Henzinger orcid: 0000-0002-2985-7724 - first_name: Daniela full_name: Rus, Daniela last_name: Rus citation: ama: 'Lechner M, Zikelic D, Chatterjee K, Henzinger TA, Rus D. Quantization-aware interval bound propagation for training certifiably robust quantized neural networks. In: Proceedings of the 37th AAAI Conference on Artificial Intelligence. Vol 37. Association for the Advancement of Artificial Intelligence; 2023:14964-14973. doi:10.1609/aaai.v37i12.26747' apa: 'Lechner, M., Zikelic, D., Chatterjee, K., Henzinger, T. A., & Rus, D. (2023). Quantization-aware interval bound propagation for training certifiably robust quantized neural networks. In Proceedings of the 37th AAAI Conference on Artificial Intelligence (Vol. 37, pp. 14964–14973). Washington, DC, United States: Association for the Advancement of Artificial Intelligence. https://doi.org/10.1609/aaai.v37i12.26747' chicago: Lechner, Mathias, Dorde Zikelic, Krishnendu Chatterjee, Thomas A Henzinger, and Daniela Rus. “Quantization-Aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks.” In Proceedings of the 37th AAAI Conference on Artificial Intelligence, 37:14964–73. Association for the Advancement of Artificial Intelligence, 2023. https://doi.org/10.1609/aaai.v37i12.26747. ieee: M. Lechner, D. Zikelic, K. Chatterjee, T. A. Henzinger, and D. Rus, “Quantization-aware interval bound propagation for training certifiably robust quantized neural networks,” in Proceedings of the 37th AAAI Conference on Artificial Intelligence, Washington, DC, United States, 2023, vol. 37, no. 12, pp. 14964–14973. ista: 'Lechner M, Zikelic D, Chatterjee K, Henzinger TA, Rus D. 2023. Quantization-aware interval bound propagation for training certifiably robust quantized neural networks. Proceedings of the 37th AAAI Conference on Artificial Intelligence. AAAI: Conference on Artificial Intelligence vol. 37, 14964–14973.' mla: Lechner, Mathias, et al. “Quantization-Aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks.” Proceedings of the 37th AAAI Conference on Artificial Intelligence, vol. 37, no. 12, Association for the Advancement of Artificial Intelligence, 2023, pp. 14964–73, doi:10.1609/aaai.v37i12.26747. short: M. Lechner, D. Zikelic, K. Chatterjee, T.A. Henzinger, D. Rus, in:, Proceedings of the 37th AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence, 2023, pp. 14964–14973. conference: end_date: 2023-02-14 location: Washington, DC, United States name: 'AAAI: Conference on Artificial Intelligence' start_date: 2023-02-07 date_created: 2023-08-27T22:01:17Z date_published: 2023-06-26T00:00:00Z date_updated: 2025-07-14T09:09:56Z day: '26' department: - _id: ToHe - _id: KrCh doi: 10.1609/aaai.v37i12.26747 ec_funded: 1 external_id: arxiv: - '2211.16187' intvolume: ' 37' issue: '12' language: - iso: eng main_file_link: - open_access: '1' url: https://doi.org/10.48550/arXiv.2211.16187 month: '06' oa: 1 oa_version: Preprint page: 14964-14973 project: - _id: 62781420-2b32-11ec-9570-8d9b63373d4d call_identifier: H2020 grant_number: '101020093' name: Vigilant Algorithmic Monitoring of Software - _id: 0599E47C-7A3F-11EA-A408-12923DDC885E call_identifier: H2020 grant_number: '863818' name: 'Formal Methods for Stochastic Models: Algorithms and Applications' - _id: 2564DBCA-B435-11E9-9278-68D0E5697425 call_identifier: H2020 grant_number: '665385' name: International IST Doctoral Program publication: Proceedings of the 37th AAAI Conference on Artificial Intelligence publication_identifier: isbn: - '9781577358800' publication_status: published publisher: Association for the Advancement of Artificial Intelligence quality_controlled: '1' scopus_import: '1' status: public title: Quantization-aware interval bound propagation for training certifiably robust quantized neural networks type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 volume: 37 year: '2023' ... --- _id: '14243' abstract: - lang: eng text: 'Two-player zero-sum "graph games" are central in logic, verification, and multi-agent systems. The game proceeds by placing a token on a vertex of a graph, and allowing the players to move it to produce an infinite path, which determines the winner or payoff of the game. Traditionally, the players alternate turns in moving the token. In "bidding games", however, the players have budgets and in each turn, an auction (bidding) determines which player moves the token. So far, bidding games have only been studied as full-information games. In this work we initiate the study of partial-information bidding games: we study bidding games in which a player''s initial budget is drawn from a known probability distribution. We show that while for some bidding mechanisms and objectives, it is straightforward to adapt the results from the full-information setting to the partial-information setting, for others, the analysis is significantly more challenging, requires new techniques, and gives rise to interesting results. Specifically, we study games with "mean-payoff" objectives in combination with "poorman" bidding. We construct optimal strategies for a partially-informed player who plays against a fully-informed adversary. We show that, somewhat surprisingly, the "value" under pure strategies does not necessarily exist in such games.' acknowledgement: This research was supported in part by ISF grant no.1679/21, by the ERC CoG 863818 (ForM-SMArt), and the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie Grant Agreement No. 665385. article_processing_charge: No arxiv: 1 author: - first_name: Guy full_name: Avni, Guy id: 463C8BC2-F248-11E8-B48F-1D18A9856A87 last_name: Avni orcid: 0000-0001-5588-8287 - first_name: Ismael R full_name: Jecker, Ismael R id: 85D7C63E-7D5D-11E9-9C0F-98C4E5697425 last_name: Jecker - first_name: Dorde full_name: Zikelic, Dorde id: 294AA7A6-F248-11E8-B48F-1D18A9856A87 last_name: Zikelic orcid: 0000-0002-4681-1699 citation: ama: 'Avni G, Jecker IR, Zikelic D. Bidding graph games with partially-observable budgets. In: Proceedings of the 37th AAAI Conference on Artificial Intelligence. Vol 37. ; 2023:5464-5471. doi:10.1609/aaai.v37i5.25679' apa: Avni, G., Jecker, I. R., & Zikelic, D. (2023). Bidding graph games with partially-observable budgets. In Proceedings of the 37th AAAI Conference on Artificial Intelligence (Vol. 37, pp. 5464–5471). Washington, DC, United States. https://doi.org/10.1609/aaai.v37i5.25679 chicago: Avni, Guy, Ismael R Jecker, and Dorde Zikelic. “Bidding Graph Games with Partially-Observable Budgets.” In Proceedings of the 37th AAAI Conference on Artificial Intelligence, 37:5464–71, 2023. https://doi.org/10.1609/aaai.v37i5.25679. ieee: G. Avni, I. R. Jecker, and D. Zikelic, “Bidding graph games with partially-observable budgets,” in Proceedings of the 37th AAAI Conference on Artificial Intelligence, Washington, DC, United States, 2023, vol. 37, no. 5, pp. 5464–5471. ista: 'Avni G, Jecker IR, Zikelic D. 2023. Bidding graph games with partially-observable budgets. Proceedings of the 37th AAAI Conference on Artificial Intelligence. AAAI: Conference on Artificial Intelligence vol. 37, 5464–5471.' mla: Avni, Guy, et al. “Bidding Graph Games with Partially-Observable Budgets.” Proceedings of the 37th AAAI Conference on Artificial Intelligence, vol. 37, no. 5, 2023, pp. 5464–71, doi:10.1609/aaai.v37i5.25679. short: G. Avni, I.R. Jecker, D. Zikelic, in:, Proceedings of the 37th AAAI Conference on Artificial Intelligence, 2023, pp. 5464–5471. conference: end_date: 2023-02-14 location: Washington, DC, United States name: 'AAAI: Conference on Artificial Intelligence' start_date: 2023-02-07 date_created: 2023-08-27T22:01:18Z date_published: 2023-06-27T00:00:00Z date_updated: 2025-07-14T09:09:56Z day: '27' department: - _id: ToHe - _id: KrCh doi: 10.1609/aaai.v37i5.25679 ec_funded: 1 external_id: arxiv: - '2211.13626' intvolume: ' 37' issue: '5' language: - iso: eng main_file_link: - open_access: '1' url: https://doi.org/10.1609/aaai.v37i5.25679 month: '06' oa: 1 oa_version: Published Version page: 5464-5471 project: - _id: 0599E47C-7A3F-11EA-A408-12923DDC885E call_identifier: H2020 grant_number: '863818' name: 'Formal Methods for Stochastic Models: Algorithms and Applications' - _id: 2564DBCA-B435-11E9-9278-68D0E5697425 call_identifier: H2020 grant_number: '665385' name: International IST Doctoral Program publication: Proceedings of the 37th AAAI Conference on Artificial Intelligence publication_identifier: isbn: - '9781577358800' publication_status: published quality_controlled: '1' scopus_import: '1' status: public title: Bidding graph games with partially-observable budgets type: conference user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87 volume: 37 year: '2023' ...