{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:11:31Z","timestamp":1774631491090,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T00:00:00Z","timestamp":1723420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ericsson","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Mitacs","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,12]]},"DOI":"10.1145\/3673038.3673137","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T18:29:01Z","timestamp":1723141741000},"page":"138-147","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Distributed Minimax Fair Optimization over Hierarchical Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8552-5598","authenticated-orcid":false,"given":"Wen","family":"Xu","sequence":"first","affiliation":[{"name":"University of Toronto, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1375-8382","authenticated-orcid":false,"given":"Juncheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1800-1322","authenticated-orcid":false,"given":"Ben","family":"Liang","sequence":"additional","affiliation":[{"name":"University of Toronto, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3539-9624","authenticated-orcid":false,"given":"Gary","family":"Boudreau","sequence":"additional","affiliation":[{"name":"Ericsson, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9785-3530","authenticated-orcid":false,"given":"Hamza","family":"Sokun","sequence":"additional","affiliation":[{"name":"Ericsson, Canada"}]}],"member":"320","published-online":{"date-parts":[[2024,8,12]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611971132"},{"key":"e_1_3_2_2_2_1","unstructured":"Barry Becker and Ronny Kohavi. 1996. Adult. UCI Machine Learning Repository."},{"key":"e_1_3_2_2_3_1","volume-title":"Proc. of the SysML Conf.","author":"Bonawitz Keith","year":"2019","unstructured":"Keith Bonawitz, Hubert Eichner, Wolfgang Grieskamp, Dzmitry Huba, Alex Ingerman, 2019. Towards federated learning at scale: System design. In Proc. of the SysML Conf."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"e_1_3_2_2_5_1","volume-title":"Proc. of ICLR.","author":"Castiglia Timothy","year":"2021","unstructured":"Timothy Castiglia, Anirban Das, and Stacy Patterson. 2021. Multi-level local SGD: Distributed SGD for heterogeneous hierarchical networks. In Proc. of ICLR."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966217"},{"key":"e_1_3_2_2_7_1","volume-title":"Proc. of NeurIPS.","author":"Daskalakis Constantinos","year":"2018","unstructured":"Constantinos Daskalakis and Ioannis Panageas. 2018. The limit points of (optimistic) gradient descent in min-max optimization. In Proc. of NeurIPS."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1137\/18M1178244"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(72)90002-X"},{"key":"e_1_3_2_2_10_1","volume-title":"Proc. of NeurIPS.","author":"Deng Yuyang","year":"2020","unstructured":"Yuyang Deng, Mohammad\u00a0Mahdi Kamani, and Mehrdad Mahdavi. 2020. Distributionally robust federated averaging. In Proc. of NeurIPS."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1214\/20-AOS2004"},{"key":"e_1_3_2_2_12_1","volume-title":"Proc. of NeurIPS.","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, 2014. Generative adversarial nets. In Proc. of NeurIPS."},{"key":"e_1_3_2_2_13_1","volume-title":"Proc. of NeurIPS.","author":"Haghtalab Nika","year":"2022","unstructured":"Nika Haghtalab, Michael Jordan, and Eric Zhao. 2022. On-demand sampling: Learning optimally from multiple distributions. In Proc. of NeurIPS."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"e_1_3_2_2_15_1","volume-title":"Proc. of ICML.","author":"Karimireddy Sai\u00a0Praneeth","year":"2020","unstructured":"Sai\u00a0Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank Reddi, Sebastian Stich, 2020. SCAFFOLD: Stochastic controlled averaging for federated learning. In Proc. of ICML."},{"key":"e_1_3_2_2_16_1","first-page":"747","article-title":"The extragradient method for finding saddle points and other problems","volume":"12","author":"Korpelevich M","year":"1976","unstructured":"Galina\u00a0M Korpelevich. 1976. The extragradient method for finding saddle points and other problems. Matecon 12 (1976), 747\u2013756.","journal-title":"Matecon"},{"key":"e_1_3_2_2_17_1","volume-title":"MNIST handwritten digit database. ATT Labs [Online]. Available: http:\/\/yann.lecun.com\/exdb\/mnist","author":"LeCun Yann","year":"2010","unstructured":"Yann LeCun, Corinna Cortes, and CJ Burges. 2010. MNIST handwritten digit database. ATT Labs [Online]. Available: http:\/\/yann.lecun.com\/exdb\/mnist (2010)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"e_1_3_2_2_19_1","volume-title":"Proc. of ICLR.","author":"Li Tian","year":"2020","unstructured":"Tian Li, Maziar Sanjabi, Ahmad Beirami, and Virginia Smith. 2020. Fair resource allocation in federated learning. In Proc. of ICLR."},{"key":"e_1_3_2_2_20_1","volume-title":"Proc. of ICML.","author":"Lin Tianyi","year":"2020","unstructured":"Tianyi Lin, Chi Jin, and Michael Jordan. 2020. On gradient descent ascent for nonconvex-concave minimax problems. In Proc. of ICML."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICC40277.2020.9148862"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3190512"},{"key":"e_1_3_2_2_23_1","volume-title":"Proc. of AISTATS.","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise\u00a0Ag\u00fcera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Proc. of AISTATS."},{"key":"e_1_3_2_2_24_1","volume-title":"Proc. of ICLR.","author":"Mertikopoulos Panayotis","year":"2019","unstructured":"Panayotis Mertikopoulos, Bruno Lecouat, Houssam Zenati, Chuan-Sheng Foo, Vijay Chandrasekhar, 2019. Optimistic mirror descent in saddle-point problems: Going the extra(-gradient) mile. In Proc. of ICLR."},{"key":"e_1_3_2_2_25_1","volume-title":"Proc. of ICML.","author":"Mohri Mehryar","year":"2019","unstructured":"Mehryar Mohri, Gary Sivek, and Ananda\u00a0Theertha Suresh. 2019. Agnostic federated learning. In Proc. of ICML."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"John Nash. 1951. Non-cooperative games. Ann. of Math. (1951) 286\u2013295.","DOI":"10.2307\/1969529"},{"key":"e_1_3_2_2_27_1","volume-title":"Algorithmic game theory","author":"Nisan Noam","unstructured":"Noam Nisan, Tim Roughgarden, \u00c9va Tardos, and Vijay\u00a0V. Vazirani. 2007. Algorithmic game theory. Cambridge University Press."},{"key":"e_1_3_2_2_28_1","volume-title":"Proc. of NeurIPS.","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, 2019. PyTorch: An imperative style, high-performance deep learning library. In Proc. of NeurIPS."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2021.1895152"},{"key":"e_1_3_2_2_30_1","volume-title":"Distributionally robust optimization: A review. arXiv preprint arXiv:1908.05659","author":"Rahimian Hamed","year":"2019","unstructured":"Hamed Rahimian and Sanjay Mehrotra. 2019. Distributionally robust optimization: A review. arXiv preprint arXiv:1908.05659 (2019)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.5555\/2789272.2789278"},{"key":"e_1_3_2_2_32_1","volume-title":"Proc. of ICLR.","author":"Sagawa Shiori","year":"2020","unstructured":"Shiori Sagawa, Pang\u00a0Wei Koh, Tatsunori\u00a0B. Hashimoto, and Percy Liang. 2020. Distributionally robust neural networks. In Proc. of ICLR."},{"key":"e_1_3_2_2_33_1","volume-title":"Proc. of NeurIPS.","author":"Schmidt Ludwig","year":"2018","unstructured":"Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, and Aleksander Madry. 2018. Adversarially robust generalization requires more data. In Proc. of NeurIPS."},{"key":"e_1_3_2_2_34_1","volume-title":"Proc. of ICLR.","author":"Stich U","year":"2019","unstructured":"Sebastian\u00a0U Stich. 2019. Local SGD converges fast and communicates little. In Proc. of ICLR."},{"key":"e_1_3_2_2_35_1","volume-title":"Zur theorie der gesellschaftsspiele. 119, 1","author":"von Neumann John","year":"1928","unstructured":"John von Neumann. 1928. Zur theorie der gesellschaftsspiele. 119, 1 (1928), 295\u2013320."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20832"},{"key":"e_1_3_2_2_37_1","unstructured":"Han Xiao Kashif Rasul and Roland Vollgraf. 2017. Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. https:\/\/github.com\/zalandoresearch\/fashion-mnist."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"}],"event":{"name":"ICPP '24: the 53rd International Conference on Parallel Processing","location":"Gotland Sweden","acronym":"ICPP '24"},"container-title":["Proceedings of the 53rd International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673137","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3673038.3673137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:30:57Z","timestamp":1758648657000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3673038.3673137"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,12]]},"references-count":38,"alternative-id":["10.1145\/3673038.3673137","10.1145\/3673038"],"URL":"https:\/\/doi.org\/10.1145\/3673038.3673137","relation":{},"subject":[],"published":{"date-parts":[[2024,8,12]]},"assertion":[{"value":"2024-08-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}