[{"day":"15","arxiv":1,"abstract":[{"lang":"eng","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."}],"citation":{"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.","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.","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.","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.","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.","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.","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."},"year":"2022","date_updated":"2023-09-06T10:29:42Z","external_id":{"arxiv":["2204.04440"]},"volume":35,"extern":"1","department":[{"_id":"FrLo"}],"date_created":"2023-08-21T12:12:42Z","article_processing_charge":"No","publication_status":"published","intvolume":"        35","title":"Are two heads the same as one? Identifying disparate treatment in fair neural networks","alternative_title":["Advances in Neural Information Processing Systems"],"scopus_import":"1","_id":"14106","author":[{"full_name":"Lohaus, Michael","first_name":"Michael","last_name":"Lohaus"},{"last_name":"Kleindessner","first_name":"Matthäus","full_name":"Kleindessner, Matthäus"},{"last_name":"Kenthapadi","first_name":"Krishnaram","full_name":"Kenthapadi, Krishnaram"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","orcid":"0000-0002-4850-0683","full_name":"Locatello, Francesco","first_name":"Francesco","last_name":"Locatello"},{"last_name":"Russell","first_name":"Chris","full_name":"Russell, Chris"}],"publisher":"Neural Information Processing Systems Foundation","quality_controlled":"1","page":"16548-16562","publication_identifier":{"isbn":["9781713871088"]},"oa":1,"type":"conference","date_published":"2022-12-15T00:00:00Z","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2204.04440"}],"status":"public","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","oa_version":"Preprint","month":"12","publication":"36th Conference on Neural Information Processing Systems","conference":{"end_date":"2022-12-09","location":"New Orleans, LA, United States","start_date":"2022-11-28","name":"NeurIPS: Neural Information Processing Systems"},"language":[{"iso":"eng"}]},{"oa_version":"Preprint","month":"12","publication":"36th Conference on Neural Information Processing Systems","conference":{"name":"NeurIPS: Neural Information Processing Systems","start_date":"2022-11-28","location":"New Orleans, LA, United States","end_date":"2022-12-09"},"language":[{"iso":"eng"}],"publication_identifier":{"isbn":["9781713871088"]},"oa":1,"type":"conference","date_published":"2022-12-15T00:00:00Z","main_file_link":[{"open_access":"1","url":"https://arxiv.org/abs/2207.09239"}],"status":"public","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","article_processing_charge":"No","date_created":"2023-08-22T14:01:13Z","department":[{"_id":"FrLo"}],"publication_status":"published","intvolume":"        35","title":"Assaying out-of-distribution generalization in transfer learning","alternative_title":["Advances in Neural Information Processing Systems"],"scopus_import":"1","_id":"14173","author":[{"first_name":"Florian","last_name":"Wenzel","full_name":"Wenzel, Florian"},{"first_name":"Andrea","last_name":"Dittadi","full_name":"Dittadi, Andrea"},{"last_name":"Gehler","first_name":"Peter Vincent","full_name":"Gehler, Peter Vincent"},{"full_name":"Carl-Johann Simon-Gabriel, Carl-Johann Simon-Gabriel","first_name":"Carl-Johann Simon-Gabriel","last_name":"Carl-Johann Simon-Gabriel"},{"first_name":"Max","last_name":"Horn","full_name":"Horn, Max"},{"full_name":"Zietlow, Dominik","last_name":"Zietlow","first_name":"Dominik"},{"full_name":"Kernert, David","first_name":"David","last_name":"Kernert"},{"last_name":"Russell","first_name":"Chris","full_name":"Russell, Chris"},{"first_name":"Thomas","last_name":"Brox","full_name":"Brox, Thomas"},{"last_name":"Schiele","first_name":"Bernt","full_name":"Schiele, Bernt"},{"last_name":"Schölkopf","first_name":"Bernhard","full_name":"Schölkopf, Bernhard"},{"id":"26cfd52f-2483-11ee-8040-88983bcc06d4","first_name":"Francesco","last_name":"Locatello","orcid":"0000-0002-4850-0683","full_name":"Locatello, Francesco"}],"publisher":"Neural Information Processing Systems Foundation","quality_controlled":"1","page":"7181-7198","day":"15","arxiv":1,"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"}],"citation":{"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.","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.","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.","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.","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.","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."},"year":"2022","date_updated":"2023-09-06T10:34:43Z","external_id":{"arxiv":["2207.09239"]},"volume":35,"extern":"1"},{"acknowledgement":"The authors were partially supported by the 2019 Lopez-Loreta prize, and they would like to thank\r\nQuynh Nguyen, Mahdi Soltanolkotabi and Adel Javanmard for helpful discussions.\r\n","volume":35,"citation":{"ista":"Bombari S, Amani MH, Mondelli M. 2022. Memorization and optimization in deep neural networks with minimum over-parameterization. 36th Conference on Neural Information Processing Systems. vol. 35, 7628–7640.","mla":"Bombari, Simone, et al. “Memorization and Optimization in Deep Neural Networks with Minimum Over-Parameterization.” <i>36th Conference on Neural Information Processing Systems</i>, vol. 35, Curran Associates, 2022, pp. 7628–40.","short":"S. Bombari, M.H. Amani, M. Mondelli, in:, 36th Conference on Neural Information Processing Systems, Curran Associates, 2022, pp. 7628–7640.","ieee":"S. Bombari, M. H. Amani, and M. Mondelli, “Memorization and optimization in deep neural networks with minimum over-parameterization,” in <i>36th Conference on Neural Information Processing Systems</i>, 2022, vol. 35, pp. 7628–7640.","chicago":"Bombari, Simone, Mohammad Hossein Amani, and Marco Mondelli. “Memorization and Optimization in Deep Neural Networks with Minimum Over-Parameterization.” In <i>36th Conference on Neural Information Processing Systems</i>, 35:7628–40. Curran Associates, 2022.","ama":"Bombari S, Amani MH, Mondelli M. Memorization and optimization in deep neural networks with minimum over-parameterization. In: <i>36th Conference on Neural Information Processing Systems</i>. Vol 35. Curran Associates; 2022:7628-7640.","apa":"Bombari, S., Amani, M. H., &#38; Mondelli, M. (2022). Memorization and optimization in deep neural networks with minimum over-parameterization. In <i>36th Conference on Neural Information Processing Systems</i> (Vol. 35, pp. 7628–7640). Curran Associates."},"year":"2022","date_updated":"2024-09-10T13:03:19Z","external_id":{"arxiv":["2205.10217"]},"day":"24","arxiv":1,"abstract":[{"lang":"eng","text":"The Neural Tangent Kernel (NTK) has emerged as a powerful tool to provide memorization, optimization and generalization guarantees in deep neural networks. A line of work has studied the NTK spectrum for two-layer and deep networks with at least a layer with Ω(N) neurons, N being the number of training samples. Furthermore, there is increasing evidence suggesting that deep networks with sub-linear layer widths are powerful memorizers and optimizers, as long as the number of parameters exceeds the number of samples. Thus, a natural open question is whether the NTK is well conditioned in such a challenging sub-linear setup. In this paper, we answer this question in the affirmative. Our key technical contribution is a lower bound on the smallest NTK eigenvalue for deep networks with the minimum possible over-parameterization: the number of parameters is roughly Ω(N) and, hence, the number of neurons is as little as Ω(N−−√). To showcase the applicability of our NTK bounds, we provide two results concerning memorization capacity and optimization guarantees for gradient descent training."}],"quality_controlled":"1","page":"7628-7640","publisher":"Curran Associates","_id":"12537","author":[{"id":"ca726dda-de17-11ea-bc14-f9da834f63aa","full_name":"Bombari, Simone","last_name":"Bombari","first_name":"Simone"},{"first_name":"Mohammad Hossein","last_name":"Amani","full_name":"Amani, Mohammad Hossein"},{"id":"27EB676C-8706-11E9-9510-7717E6697425","first_name":"Marco","last_name":"Mondelli","orcid":"0000-0002-3242-7020","full_name":"Mondelli, Marco"}],"article_processing_charge":"No","department":[{"_id":"MaMo"}],"date_created":"2023-02-10T13:46:37Z","publication_status":"published","intvolume":"        35","title":"Memorization and optimization in deep neural networks with minimum over-parameterization","main_file_link":[{"url":" https://doi.org/10.48550/arXiv.2205.10217","open_access":"1"}],"status":"public","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","type":"conference","date_published":"2022-07-24T00:00:00Z","publication_identifier":{"isbn":["9781713871088"]},"oa":1,"language":[{"iso":"eng"}],"publication":"36th Conference on Neural Information Processing Systems","project":[{"name":"Prix Lopez-Loretta 2019 - Marco Mondelli","_id":"059876FA-7A3F-11EA-A408-12923DDC885E"}],"oa_version":"Preprint","month":"07"}]