{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T21:11:20Z","timestamp":1769548280502,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["NSF AI Institute (AI-EDGE) CNS-2112471"],"award-info":[{"award-number":["NSF AI Institute (AI-EDGE) CNS-2112471"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2312836"],"award-info":[{"award-number":["CNS-2312836"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2106933"],"award-info":[{"award-number":["CNS-2106933"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2106932"],"award-info":[{"award-number":["CNS-2106932"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-1955535"],"award-info":[{"award-number":["CNS-1955535"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-1901057"],"award-info":[{"award-number":["CNS-1901057"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["ECCS-2113860"],"award-info":[{"award-number":["ECCS-2113860"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2324052"],"award-info":[{"award-number":["2324052"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CAREER CNS-2110259"],"award-info":[{"award-number":["CAREER CNS-2110259"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["ECCS-2331104"],"award-info":[{"award-number":["ECCS-2331104"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-21-1-0244"],"award-info":[{"award-number":["W911NF-21-1-0244"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-23-2-0225"],"award-info":[{"award-number":["W911NF-23-2-0225"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DARPA","award":["D24AP00265"],"award-info":[{"award-number":["D24AP00265"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,14]]},"DOI":"10.1145\/3641512.3686382","type":"proceedings-article","created":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T21:11:22Z","timestamp":1727817082000},"page":"141-150","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Can We Theoretically Quantify the Impacts of Local Updates on the Generalization Performance of Federated Learning?"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4569-3539","authenticated-orcid":false,"given":"Peizhong","family":"Ju","sequence":"first","affiliation":[{"name":"The Ohio State University, Columbus, Ohio, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3245-2728","authenticated-orcid":false,"given":"Haibo","family":"Yang","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology, Rochester, New York, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8844-3233","authenticated-orcid":false,"given":"Jia","family":"Liu","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, Ohio, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8635-2992","authenticated-orcid":false,"given":"Yingbin","family":"Liang","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, Ohio, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4606-6879","authenticated-orcid":false,"given":"Ness","family":"Shroff","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, Ohio, United States of America"}]}],"member":"320","published-online":{"date-parts":[[2024,10]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology (TIST), 10(2):1--19","author":"Yang Qiang","year":"2019","unstructured":"Qiang Yang, Yang Liu, Tianjian Chen, and Yongxin Tong. Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology (TIST), 10(2):1--19, 2019."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41666-020-00082-4"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63076-8_17"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3090430"},{"key":"e_1_3_2_2_5_1","volume-title":"PMLR","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics, pages 1273-1282. PMLR, 2017."},{"key":"e_1_3_2_2_6_1","first-page":"654","volume-title":"Proceedings, Part XXIII","author":"Caldarola Debora","year":"2022","unstructured":"Debora Caldarola, Barbara Caputo, and Marco Ciccone. Improving generalization in federated learning by seeking flat minima. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23--27, 2022, Proceedings, Part XXIII, pages 654-672. Springer, 2022."},{"key":"e_1_3_2_2_7_1","volume-title":"Federated learning with non-iid data. arXiv preprint arXiv:1806.00582","author":"Zhao Yue","year":"2018","unstructured":"Yue Zhao, Meng Li, Liangzhen Lai, Naveen Suda, Damon Civin, and Vikas Chandra. Federated learning with non-iid data. arXiv preprint arXiv:1806.00582, 2018."},{"key":"e_1_3_2_2_8_1","volume-title":"On the unreasonable effectiveness of federated averaging with heterogeneous data. arXiv preprint arXiv:2206.04723","author":"Wang Jianyu","year":"2022","unstructured":"Jianyu Wang, Rudrajit Das, Gauri Joshi, Satyen Kale, Zheng Xu, and Tong Zhang. On the unreasonable effectiveness of federated averaging with heterogeneous data. arXiv preprint arXiv:2206.04723, 2022."},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the 8th International Conference on Learning Representations","author":"Lin Tao","year":"2019","unstructured":"Tao Lin, Sebastian Urban Stich, Kumar Kshitij Patel, and Martin Jaggi. Don't use large mini-batches, use local sgd. In Proceedings of the 8th International Conference on Learning Representations, 2019."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/3546258.3546471"},{"key":"e_1_3_2_2_11_1","volume-title":"Trade-offs of local sgd at scale: An empirical study. arXiv preprint arXiv:2110.08133","author":"Gonzalez Ortiz Jose Javier","year":"2021","unstructured":"Jose Javier Gonzalez Ortiz, Jonathan Frankle, Mike Rabbat, Ari Morcos, and Nicolas Ballas. Trade-offs of local sgd at scale: An empirical study. arXiv preprint arXiv:2110.08133, 2021."},{"key":"e_1_3_2_2_12_1","volume-title":"International Conference on Learning Representations","author":"Yuan Honglin","year":"2022","unstructured":"Honglin Yuan, Warren Richard Morningstar, Lin Ning, and Karan Singhal. What do we mean by generalization in federated learning? In International Conference on Learning Representations, 2022."},{"key":"e_1_3_2_2_13_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Hu Xiaolin","year":"2023","unstructured":"Xiaolin Hu, Shaojie Li, and Yong Liu. Generalization bounds for federated learning: Fast rates, unparticipating clients and unbounded losses. In The Eleventh International Conference on Learning Representations, 2023."},{"key":"e_1_3_2_2_14_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Gu Xinran","year":"2022","unstructured":"Xinran Gu, Kaifeng Lyu, Longbo Huang, and Sanjeev Arora. Why (and when) does local sgd generalize better than sgd? In The Eleventh International Conference on Learning Representations, 2022."},{"key":"e_1_3_2_2_15_1","volume-title":"Understanding generalization of federated learning via stability: Heterogeneity matters. arXiv preprint arXiv:2306.03824","author":"Sun Zhenyu","year":"2023","unstructured":"Zhenyu Sun, Xiaochun Niu, and Ermin Wei. Understanding generalization of federated learning via stability: Heterogeneity matters. arXiv preprint arXiv:2306.03824, 2023."},{"key":"e_1_3_2_2_16_1","volume-title":"Federated learning you may communicate less often! arXiv preprint arXiv:2306.05862","author":"Sefidgaran Milad","year":"2023","unstructured":"Milad Sefidgaran, Romain Chor, Abdellatif Zaidi, and Yijun Wan. Federated learning you may communicate less often! arXiv preprint arXiv:2306.05862, 2023."},{"key":"e_1_3_2_2_17_1","first-page":"1","volume-title":"Journal of the American Statistical Association","author":"Li Sai","year":"2023","unstructured":"Sai Li, Linjun Zhang, T Tony Cai, and Hongzhe Li. Estimation and inference for high-dimensional generalized linear models with knowledge transfer. Journal of the American Statistical Association, pages 1--12, 2023."},{"key":"e_1_3_2_2_18_1","first-page":"7956","article-title":"Overfitting can be harmless for basis pursuit, but only to a degree","volume":"33","author":"Ju Peizhong","year":"2020","unstructured":"Peizhong Ju, Xiaojun Lin, and Jia Liu. Overfitting can be harmless for basis pursuit, but only to a degree. Advances in Neural Information Processing Systems, 33:7956--7967, 2020.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1137\/20M1336072"},{"key":"e_1_3_2_2_20_1","first-page":"541","volume-title":"International Conference on Machine Learning","author":"Belkin Mikhail","year":"2018","unstructured":"Mikhail Belkin, Siyuan Ma, and Soumik Mandal. To understand deep learning we need to understand kernel learning. In International Conference on Machine Learning, pages 541--549, 2018."},{"key":"e_1_3_2_2_21_1","volume-title":"Two models of double descent for weak features. arXiv preprint arXiv:1903.07571","author":"Belkin Mikhail","year":"2019","unstructured":"Mikhail Belkin, Daniel Hsu, and Ji Xu. Two models of double descent for weak features. arXiv preprint arXiv:1903.07571, 2019."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1907378117"},{"key":"e_1_3_2_2_23_1","volume-title":"Surprises in high-dimensional ridgeless least squares interpolation. arXiv preprint arXiv:1903.08560","author":"Hastie Trevor","year":"2019","unstructured":"Trevor Hastie, Andrea Montanari, Saharon Rosset, and Ryan J Tibshirani. Surprises in high-dimensional ridgeless least squares interpolation. arXiv preprint arXiv:1903.08560, 2019."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849614"},{"key":"e_1_3_2_2_25_1","volume-title":"Understanding overfitting peaks in generalization error: Analytical risk curves for l2 and l1 penalized interpolation. arXiv preprint arXiv:1906.03667","author":"Mitra Partha P","year":"2019","unstructured":"Partha P Mitra. Understanding overfitting peaks in generalization error: Analytical risk curves for l2 and l1 penalized interpolation. arXiv preprint arXiv:1906.03667, 2019."},{"key":"e_1_3_2_2_26_1","volume-title":"Ameet Talwalkar, and Virginia Smith. Federated learning: Challenges, methods, and future directions. arXiv preprint arXiv:1908.07873","author":"Li Tian","year":"2019","unstructured":"Tian Li, Anit Kumar Sahu, Ameet Talwalkar, and Virginia Smith. Federated learning: Challenges, methods, and future directions. arXiv preprint arXiv:1908.07873, 2019."},{"key":"e_1_3_2_2_27_1","volume-title":"Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology (TIST), 10(2):1--19","author":"Yang Qiang","year":"2019","unstructured":"Qiang Yang, Yang Liu, Tianjian Chen, and Yongxin Tong. Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology (TIST), 10(2):1--19, 2019."},{"key":"e_1_3_2_2_28_1","volume-title":"Keith Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, et al. Advances and open problems in federated learning. arXiv preprint arXiv:1912.04977","author":"Kairouz Peter","year":"2019","unstructured":"Peter Kairouz, H Brendan McMahan, Brendan Avent, Aur\u00e9lien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Keith Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, et al. Advances and open problems in federated learning. arXiv preprint arXiv:1912.04977, 2019."},{"key":"e_1_3_2_2_29_1","volume-title":"Communication-efficient learning of deep networks from decentralized data. arXiv preprint arXiv:1602.05629","author":"McMahan H Brendan","year":"2016","unstructured":"H Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, et al. Communication-efficient learning of deep networks from decentralized data. arXiv preprint arXiv:1602.05629, 2016."},{"key":"e_1_3_2_2_30_1","volume-title":"Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. Federated optimization in heterogeneous networks. arXiv preprint arXiv:1812.06127","author":"Li Tian","year":"2018","unstructured":"Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. Federated optimization in heterogeneous networks. arXiv preprint arXiv:1812.06127, 2018."},{"key":"e_1_3_2_2_31_1","volume-title":"Fedpd: A federated learning framework with optimal rates and adaptivity to non-iid data. arXiv preprint arXiv:2005.11418","author":"Zhang Xinwei","year":"2020","unstructured":"Xinwei Zhang, Mingyi Hong, Sairaj Dhople, Wotao Yin, and Yang Liu. Fedpd: A federated learning framework with optimal rates and adaptivity to non-iid data. arXiv preprint arXiv:2005.11418, 2020."},{"key":"e_1_3_2_2_32_1","series-title":"Proceedings of Machine Learning Research","first-page":"5132","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Karimireddy Sai Praneeth","year":"2020","unstructured":"Sai Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank Reddi, Sebastian Stich, and Ananda Theertha Suresh. SCAFFOLD: Stochastic controlled averaging for federated learning. In Hal Daum\u00e9 III and Aarti Singh, editors, Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 5132-5143. PMLR, 13--18 Jul 2020."},{"key":"e_1_3_2_2_33_1","volume-title":"Mime: Mimicking centralized stochastic algorithms in federated learning. arXiv preprint arXiv:2008.03606","author":"Karimireddy Sai Praneeth","year":"2020","unstructured":"Sai Praneeth Karimireddy, Martin Jaggi, Satyen Kale, Mehryar Mohri, Sashank J Reddi, Sebastian U Stich, and Ananda Theertha Suresh. Mime: Mimicking centralized stochastic algorithms in federated learning. arXiv preprint arXiv:2008.03606, 2020."},{"key":"e_1_3_2_2_34_1","volume-title":"International Conference on Learning Representations","author":"Emre Acar Durmus Alp","year":"2021","unstructured":"Durmus Alp Emre Acar, Yue Zhao, Ramon Matas Navarro, Matthew Mattina, Paul N Whatmough, and Venkatesh Saligrama. Federated learning based on dynamic regularization. In International Conference on Learning Representations, 2021."},{"key":"e_1_3_2_2_35_1","volume-title":"International Conference on Learning Representations","author":"Yang Haibo","year":"2021","unstructured":"Haibo Yang, Minghong Fang, and Jia Liu. Achieving linear speedup with partial worker participation in non-{iid} federated learning. In International Conference on Learning Representations, 2021."},{"key":"e_1_3_2_2_36_1","first-page":"25331","volume-title":"International Conference on Machine Learning","author":"Yang Haibo","year":"2022","unstructured":"Haibo Yang, Xin Zhang, Prashant Khanduri, and Jia Liu. Anarchic federated learning. In International Conference on Machine Learning, pages 25331-25363. PMLR, 2022."},{"key":"e_1_3_2_2_37_1","volume-title":"Federated pac-bayesian learning on non-iid data. arXiv preprint arXiv:2309.06683","author":"Zhao Zihao","year":"2023","unstructured":"Zihao Zhao, Yang Liu, Wenbo Ding, and Xiao-Ping Zhang. Federated pac-bayesian learning on non-iid data. arXiv preprint arXiv:2309.06683, 2023."},{"key":"e_1_3_2_2_38_1","volume-title":"More communication does not result in smaller generalization error in federated learning. arXiv preprint arXiv:2304.12216","author":"Chor Romain","year":"2023","unstructured":"Romain Chor, Milad Sefidgaran, and Abdellatif Zaidi. More communication does not result in smaller generalization error in federated learning. arXiv preprint arXiv:2304.12216, 2023."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT50566.2022.9834700"},{"key":"e_1_3_2_2_40_1","first-page":"19687","article-title":"Rate-distortion theoretic bounds on generalization error for distributed learning","volume":"35","author":"Sefidgaran Milad","year":"2022","unstructured":"Milad Sefidgaran, Romain Chor, and Abdellatif Zaidi. Rate-distortion theoretic bounds on generalization error for distributed learning. Advances in Neural Information Processing Systems, 35:19687--19702, 2022.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_41_1","first-page":"4423","volume-title":"International Conference on Machine Learning","author":"Huang Baihe","year":"2021","unstructured":"Baihe Huang, Xiaoxiao Li, Zhao Song, and Xin Yang. Fl-ntk: A neural tangent kernel-based framework for federated learning analysis. In International Conference on Machine Learning, pages 4423-4434. PMLR, 2021."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02352"},{"key":"e_1_3_2_2_43_1","first-page":"18250","volume-title":"International Conference on Machine Learning","author":"Qu Zhe","year":"2022","unstructured":"Zhe Qu, Xingyu Li, Rui Duan, Yao Liu, Bo Tang, and Zhuo Lu. Generalized federated learning via sharpness aware minimization. In International Conference on Machine Learning, pages 18250-18280. PMLR, 2022."},{"key":"e_1_3_2_2_44_1","volume-title":"The generalization error of random features regression: Precise asymptotics and double descent curve. arXiv preprint arXiv:1908.05355","author":"Mei Song","year":"2019","unstructured":"Song Mei and Andrea Montanari. The generalization error of random features regression: Precise asymptotics and double descent curve. arXiv preprint arXiv:1908.05355, 2019."},{"key":"e_1_3_2_2_45_1","first-page":"322","volume-title":"International Conference on Machine Learning","author":"Arora Sanjeev","year":"2019","unstructured":"Sanjeev Arora, Simon Du, Wei Hu, Zhiyuan Li, and Ruosong Wang. Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks. In International Conference on Machine Learning, pages 322--332, 2019."},{"key":"e_1_3_2_2_46_1","first-page":"373","volume-title":"Learning for Dynamics and Control","author":"Satpathi Siddhartha","year":"2021","unstructured":"Siddhartha Satpathi and R Srikant. The dynamics of gradient descent for over-parametrized neural networks. In Learning for Dynamics and Control, pages 373-384. PMLR, 2021."},{"key":"e_1_3_2_2_47_1","volume-title":"On the generalization power of overfitted two-layer neural tangent kernel models. arXiv preprint arXiv:2103.05243","author":"Ju Peizhong","year":"2021","unstructured":"Peizhong Ju, Xiaojun Lin, and Ness B Shroff. On the generalization power of overfitted two-layer neural tangent kernel models. arXiv preprint arXiv:2103.05243, 2021."},{"key":"e_1_3_2_2_48_1","volume-title":"On the generalization power of the overfitted three-layer neural tangent kernel model. arXiv preprint arXiv:2206.02047","author":"Ju Peizhong","year":"2022","unstructured":"Peizhong Ju, Xiaojun Lin, and Ness B Shroff. On the generalization power of the overfitted three-layer neural tangent kernel model. arXiv preprint arXiv:2206.02047, 2022."},{"key":"e_1_3_2_2_49_1","volume-title":"Advances and open problems in federated learning. Foundations and Trends\u00ae in Machine Learning, 14(1)","author":"McMahan H Brendan","year":"2021","unstructured":"H Brendan McMahan et al. Advances and open problems in federated learning. Foundations and Trends\u00ae in Machine Learning, 14(1), 2021."},{"key":"e_1_3_2_2_50_1","volume-title":"Convergence theorems for gradient descent. Lecture notes for Statistical Optimization","author":"Gower Robert M","year":"2018","unstructured":"Robert M Gower. Convergence theorems for gradient descent. Lecture notes for Statistical Optimization, 2018."},{"key":"e_1_3_2_2_51_1","volume-title":"Handbook of convergence theorems for (stochastic) gradient methods. arXiv preprint arXiv:2301.11235","author":"Garrigos Guillaume","year":"2023","unstructured":"Guillaume Garrigos and Robert M Gower. Handbook of convergence theorems for (stochastic) gradient methods. arXiv preprint arXiv:2301.11235, 2023."},{"key":"e_1_3_2_2_52_1","first-page":"1832","volume-title":"International Conference on Machine Learning","author":"Gunasekar Suriya","year":"2018","unstructured":"Suriya Gunasekar, Jason Lee, Daniel Soudry, and Nathan Srebro. Characterizing implicit bias in terms of optimization geometry. In International Conference on Machine Learning, pages 1832-1841. PMLR, 2018."},{"key":"e_1_3_2_2_53_1","volume-title":"Theory on forgetting and generalization of continual learning. arXiv preprint arXiv:2302.05836","author":"Lin Sen","year":"2023","unstructured":"Sen Lin, Peizhong Ju, Yingbin Liang, and Ness Shroff. Theory on forgetting and generalization of continual learning. arXiv preprint arXiv:2302.05836, 2023."},{"key":"e_1_3_2_2_54_1","volume-title":"Supplemental material. https:\/\/github.com\/functionadvanced\/Supp_Material\/blob\/main\/supp.pdf","author":"Ju Peizhong","year":"2024","unstructured":"Peizhong Ju, Haibo Yang, Jia Liu, Yingbin Liang, and Ness Shroff. Supplemental material. https:\/\/github.com\/functionadvanced\/Supp_Material\/blob\/main\/supp.pdf, 2024. Accessed: 2024-08-25."},{"key":"e_1_3_2_2_55_1","volume-title":"On pre-training for federated learning. arXiv preprint arXiv:2206.11488","author":"Chen Hong-You","year":"2022","unstructured":"Hong-You Chen, Cheng-Hao Tu, Ziwei Li, Han-Wei Shen, and Wei-Lun Chao. On pre-training for federated learning. arXiv preprint arXiv:2206.11488, 2022."},{"key":"e_1_3_2_2_56_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Nguyen John","year":"2023","unstructured":"John Nguyen, Jianyu Wang, Kshitiz Malik, Maziar Sanjabi, and Michael Rabbat. Where to begin? on the impact of pre-training and initialization in federated learning. In The Eleventh International Conference on Learning Representations, 2023."},{"key":"e_1_3_2_2_57_1","volume-title":"International Conference on Learning Representations","author":"Li Xiang","year":"2020","unstructured":"Xiang Li, Kaixuan Huang, Wenhao Yang, Shusen Wang, and Zhihua Zhang. On the convergence of fedavg on non-iid data. In International Conference on Learning Representations, 2020."},{"key":"e_1_3_2_2_58_1","first-page":"429","volume-title":"Proceedings of Machine Learning and Systems","volume":"2","author":"Li Tian","year":"2020","unstructured":"Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. Federated optimization in heterogeneous networks. In I. Dhillon, D. Papailiopoulos, and V. Sze, editors, Proceedings of Machine Learning and Systems, volume 2, pages 429--450, 2020."},{"key":"e_1_3_2_2_59_1","volume-title":"International Conference on Learning Representations","author":"Yang Haibo","year":"2020","unstructured":"Haibo Yang, Minghong Fang, and Jia Liu. Achieving linear speedup with partial worker participation in non-iid federated learning. In International Conference on Learning Representations, 2020."},{"key":"e_1_3_2_2_60_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Ju Peizhong","year":"2022","unstructured":"Peizhong Ju, Yingbin Liang, and Ness Shroff. Theoretical characterization of the generalization performance of overfitted meta-learning. In The Eleventh International Conference on Learning Representations, 2022."},{"key":"e_1_3_2_2_61_1","volume-title":"Generalization performance of transfer learning: Overparameterized and underparameterized regimes. arXiv preprint arXiv:2306.04901","author":"Ju Peizhong","year":"2023","unstructured":"Peizhong Ju, Sen Lin, Mark S Squillante, Yingbin Liang, and Ness B Shroff. Generalization performance of transfer learning: Overparameterized and underparameterized regimes. arXiv preprint arXiv:2306.04901, 2023."},{"key":"e_1_3_2_2_62_1","volume-title":"Meta-learning with negative learning rates. arXiv preprint arXiv:2102.00940","author":"Bernacchia Alberto","year":"2021","unstructured":"Alberto Bernacchia. Meta-learning with negative learning rates. arXiv preprint arXiv:2102.00940, 2021."}],"event":{"name":"MobiHoc '24: Twenty-fifth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing","location":"Athens Greece","acronym":"MobiHoc '24","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the Twenty-fifth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641512.3686382","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641512.3686382","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3641512.3686382","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:23Z","timestamp":1750291403000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3641512.3686382"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":62,"alternative-id":["10.1145\/3641512.3686382","10.1145\/3641512"],"URL":"https:\/\/doi.org\/10.1145\/3641512.3686382","relation":{},"subject":[],"published":{"date-parts":[[2024,10]]},"assertion":[{"value":"2024-10-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}