{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:12:06Z","timestamp":1782313926694,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T00:00:00Z","timestamp":1691107200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206058"],"award-info":[{"award-number":["62206058"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Sailing Program","award":["22YF1402900"],"award-info":[{"award-number":["22YF1402900"]}]},{"name":"Research Grants Council of Hong Kong, General Research Fund","award":["14200321"],"award-info":[{"award-number":["14200321"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,6]]},"DOI":"10.1145\/3580305.3599280","type":"proceedings-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T18:10:58Z","timestamp":1691172658000},"page":"1406-1416","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Communication Efficient Distributed Newton Method with Fast Convergence Rates"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6552-4892","authenticated-orcid":false,"given":"Chengchang","family":"Liu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8213-2294","authenticated-orcid":false,"given":"Lesi","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3641-8992","authenticated-orcid":false,"given":"Luo","family":"Luo","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7466-0384","authenticated-orcid":false,"given":"John C.S.","family":"Lui","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,8,4]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Sparse communication for distributed gradient descent. arXiv preprint arXiv:1704.05021","author":"Aji Alham Fikri","year":"2017","unstructured":"Alham Fikri Aji and Kenneth Heafield . Sparse communication for distributed gradient descent. arXiv preprint arXiv:1704.05021 , 2017 . Alham Fikri Aji and Kenneth Heafield. Sparse communication for distributed gradient descent. arXiv preprint arXiv:1704.05021, 2017."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10463-009-0242-4"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020410"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"e_1_3_2_2_6_1","volume-title":"NeurIPS","author":"Crane Rixon","year":"2019","unstructured":"Rixon Crane and Fred Roosta . DINGO : Distributed Newton-type method for gradient-norm optimization . NeurIPS , 2019 . Rixon Crane and Fred Roosta. DINGO: Distributed Newton-type method for gradient-norm optimization. NeurIPS, 2019."},{"key":"e_1_3_2_2_7_1","volume-title":"El Mahdi Chayti, and Martin Jaggi. Second-order optimization with lazy Hessians. arXiv preprint arXiv:2212.00781","author":"Doikov Nikita","year":"2022","unstructured":"Nikita Doikov , El Mahdi Chayti, and Martin Jaggi. Second-order optimization with lazy Hessians. arXiv preprint arXiv:2212.00781 , 2022 . Nikita Doikov, El Mahdi Chayti, and Martin Jaggi. Second-order optimization with lazy Hessians. arXiv preprint arXiv:2212.00781, 2022."},{"key":"e_1_3_2_2_8_1","volume-title":"Arya Mazumdar, and Kannan Ramchandran. Escaping saddle points in distributed Newton's method with communication efficiency and Byzantine resilience. arXiv preprint arXiv:2103.09424","author":"Ghosh Avishek","year":"2021","unstructured":"Avishek Ghosh , Raj Kumar Maity , Arya Mazumdar, and Kannan Ramchandran. Escaping saddle points in distributed Newton's method with communication efficiency and Byzantine resilience. arXiv preprint arXiv:2103.09424 , 2021 . Avishek Ghosh, Raj Kumar Maity, Arya Mazumdar, and Kannan Ramchandran. Escaping saddle points in distributed Newton's method with communication efficiency and Byzantine resilience. arXiv preprint arXiv:2103.09424, 2021."},{"key":"e_1_3_2_2_9_1","volume-title":"ICML","author":"Islamov Rustem","year":"2021","unstructured":"Rustem Islamov , Xun Qian , and Peter Richt\u00e1rik . Distributed second order methods with fast rates and compressed communication . In ICML , 2021 . Rustem Islamov, Xun Qian, and Peter Richt\u00e1rik. Distributed second order methods with fast rates and compressed communication. In ICML, 2021."},{"key":"e_1_3_2_2_10_1","volume-title":"Distributed Newton-type methods with communication compression and Bernoulli aggregation. arXiv preprint arXiv:2206.03588","author":"Islamov Rustem","year":"2022","unstructured":"Rustem Islamov , Xun Qian , Slavom\u00edr Hanzely , Mher Safaryan , and Peter Richt\u00e1rik . Distributed Newton-type methods with communication compression and Bernoulli aggregation. arXiv preprint arXiv:2206.03588 , 2022 . Rustem Islamov, Xun Qian, Slavom\u00edr Hanzely, Mher Safaryan, and Peter Richt\u00e1rik. Distributed Newton-type methods with communication compression and Bernoulli aggregation. arXiv preprint arXiv:2206.03588, 2022."},{"key":"e_1_3_2_2_11_1","volume-title":"ICML","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 ICML , 2020 . Sai Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank Reddi, Sebastian Stich, and Ananda Theertha Suresh. SCAFFOLD: Stochastic controlled averaging for federated learning. In ICML, 2020."},{"key":"e_1_3_2_2_12_1","volume-title":"Ananda Theertha Suresh, and Dave Bacon. Federated learning: Strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492","author":"Jakub","year":"2016","unstructured":"Jakub Konevcn?, H. Brendan McMahan , Felix X. Yu , Peter Richt\u00e1rik , Ananda Theertha Suresh, and Dave Bacon. Federated learning: Strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492 , 2016 . Jakub Konevcn?, H. Brendan McMahan, Felix X. Yu, Peter Richt\u00e1rik, Ananda Theertha Suresh, and Dave Bacon. Federated learning: Strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492, 2016."},{"key":"e_1_3_2_2_13_1","volume-title":"KDD","author":"Lim Cong Han","year":"2018","unstructured":"Ching-pei Lee, Cong Han Lim , and Stephen J. Wright . A distributed quasi-Newton algorithm for empirical risk minimization with nonsmooth regularization . In KDD , 2018 . Ching-pei Lee, Cong Han Lim, and Stephen J. Wright. A distributed quasi-Newton algorithm for empirical risk minimization with nonsmooth regularization. In KDD, 2018."},{"key":"e_1_3_2_2_14_1","volume-title":"Big learning workshop on NIPS","author":"Li Mu","year":"2013","unstructured":"Mu Li , Li Zhou , Zichao Yang , Aaron Li , Fei Xia , David G. Andersen , and Alexander Smola . Parameter server for distributed machine learning . In Big learning workshop on NIPS , 2013 . Mu Li, Li Zhou, Zichao Yang, Aaron Li, Fei Xia, David G. Andersen, and Alexander Smola. Parameter server for distributed machine learning. In Big learning workshop on NIPS, 2013."},{"key":"e_1_3_2_2_15_1","volume-title":"NIPS","author":"Li Mu","year":"2014","unstructured":"Mu Li , David G. Andersen , Alexander J. Smola , and Kai Yu . Communication efficient distributed machine learning with the parameter server . In NIPS , 2014 . Mu Li, David G. Andersen, Alexander J. Smola, and Kai Yu. Communication efficient distributed machine learning with the parameter server. In NIPS, 2014."},{"key":"e_1_3_2_2_16_1","volume-title":"ICLR","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 ICLR , 2020 . Xiang Li, Kaixuan Huang, Wenhao Yang, Shusen Wang, and Zhihua Zhang. On the convergence of FedAvg on non-iid data. In ICLR, 2020."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098136"},{"key":"e_1_3_2_2_18_1","volume-title":"Yes! local gradient steps provably lead to communication acceleration! finally! In ICML","author":"Mishchenko Konstantin","year":"2022","unstructured":"Konstantin Mishchenko , Grigory Malinovsky , Sebastian Stich , and Peter Richt\u00e1rik . ProxSkip : Yes! local gradient steps provably lead to communication acceleration! finally! In ICML , 2022 . Konstantin Mishchenko, Grigory Malinovsky, Sebastian Stich, and Peter Richt\u00e1rik. ProxSkip: Yes! local gradient steps provably lead to communication acceleration! finally! In ICML, 2022."},{"key":"e_1_3_2_2_19_1","volume-title":"NeurIPS","author":"Mitra Aritra","year":"2021","unstructured":"Aritra Mitra , Rayana Jaafar , George J. Pappas , and Hamed Hassani . Linear convergence in federated learning: Tackling client heterogeneity and sparse gradients . In NeurIPS , 2021 . Aritra Mitra, Rayana Jaafar, George J. Pappas, and Hamed Hassani. Linear convergence in federated learning: Tackling client heterogeneity and sparse gradients. In NeurIPS, 2021."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2017.2720471"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/2794613.3114269"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.5555\/3317111"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/3112681.3113165"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/b98874"},{"key":"e_1_3_2_2_25_1","volume-title":"AIDE: Fast and communication efficient distributed optimization. arXiv preprint arXiv:1608.06879","author":"Reddi Sashank J.","year":"2016","unstructured":"Sashank J. Reddi , Jakub Konevcn?, Peter Richt\u00e1rik , Barnab\u00e1s P\u00f3cz\u00f3s , and Alex Smola . AIDE: Fast and communication efficient distributed optimization. arXiv preprint arXiv:1608.06879 , 2016 . Sashank J. Reddi, Jakub Konevcn?, Peter Richt\u00e1rik, Barnab\u00e1s P\u00f3cz\u00f3s, and Alex Smola. AIDE: Fast and communication efficient distributed optimization. arXiv preprint arXiv:1608.06879, 2016."},{"key":"e_1_3_2_2_26_1","volume-title":"ICML","author":"Safaryan Mher","year":"2022","unstructured":"Mher Safaryan , Rustem Islamov , Xun Qian , and Peter Richt\u00e1rik . FedNL : Making newton-type methods applicable to federated learning . In ICML , 2022 . Mher Safaryan, Rustem Islamov, Xun Qian, and Peter Richt\u00e1rik. FedNL: Making newton-type methods applicable to federated learning. In ICML, 2022."},{"key":"e_1_3_2_2_27_1","volume-title":"ICML","author":"Shamir Ohad","year":"2014","unstructured":"Ohad Shamir , Nati Srebro , and Tong Zhang . Communication-efficient distributed optimization using an approximate Newton-type method . In ICML , 2014 . Ohad Shamir, Nati Srebro, and Tong Zhang. Communication-efficient distributed optimization using an approximate Newton-type method. In ICML, 2014."},{"key":"e_1_3_2_2_28_1","volume-title":"L1-regularized distributed optimization: A communication-efficient primal-dual framework. arXiv preprint arXiv:1512.04011","author":"Smith Virginia","year":"2015","unstructured":"Virginia Smith , Simone Forte , Michael I. Jordan , and Martin Jaggi . L1-regularized distributed optimization: A communication-efficient primal-dual framework. arXiv preprint arXiv:1512.04011 , 2015 . Virginia Smith, Simone Forte, Michael I. Jordan, and Martin Jaggi. L1-regularized distributed optimization: A communication-efficient primal-dual framework. arXiv preprint arXiv:1512.04011, 2015."},{"key":"e_1_3_2_2_29_1","volume-title":"AISTATS","author":"Soori Saeed","year":"2020","unstructured":"Saeed Soori , Konstantin Mishchenko , Aryan Mokhtari , Maryam Mehri Dehnavi , and Mert Gurbuzbalaban . DAve-QN : A distributed averaged quasi-Newton method with local superlinear convergence rate . In AISTATS , 2020 . Saeed Soori, Konstantin Mishchenko, Aryan Mokhtari, Maryam Mehri Dehnavi, and Mert Gurbuzbalaban. DAve-QN: A distributed averaged quasi-Newton method with local superlinear convergence rate. In AISTATS, 2020."},{"key":"e_1_3_2_2_30_1","volume-title":"Uribe and Ali Jadbabaie. A distributed cubic-regularized Newton method for smooth convex optimization over networks. arXiv preprint arXiv:2007.03562","author":"C\u00e9sar","year":"2020","unstructured":"C\u00e9sar A. Uribe and Ali Jadbabaie. A distributed cubic-regularized Newton method for smooth convex optimization over networks. arXiv preprint arXiv:2007.03562 , 2020 . C\u00e9sar A. Uribe and Ali Jadbabaie. A distributed cubic-regularized Newton method for smooth convex optimization over networks. arXiv preprint arXiv:2007.03562, 2020."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377454"},{"key":"e_1_3_2_2_32_1","volume-title":"NeurIPS","author":"Wang Shusen","year":"2018","unstructured":"Shusen Wang , Fred Roosta , Peng Xu , and Michael W. Mahoney . GIANT: Globally improved approximate Newton method for distributed optimization . In NeurIPS , 2018 . Shusen Wang, Fred Roosta, Peng Xu, and Michael W. Mahoney. GIANT: Globally improved approximate Newton method for distributed optimization. In NeurIPS, 2018."},{"key":"e_1_3_2_2_33_1","volume-title":"NeurIPS","author":"Wangni Jianqiao","year":"2018","unstructured":"Jianqiao Wangni , Jialei Wang , Ji Liu , and Tong Zhang . Gradient sparsification for communication-efficient distributed optimization . In NeurIPS , 2018 . Jianqiao Wangni, Jialei Wang, Ji Liu, and Tong Zhang. Gradient sparsification for communication-efficient distributed optimization. In NeurIPS, 2018."},{"key":"e_1_3_2_2_34_1","volume-title":"ICML","author":"Yan Ling","year":"2014","unstructured":"Ling Yan , Wu-Jun Li , Gui-Rong Xue , and Dingyi Han . Coupled group lasso for web-scale CTR prediction in display advertising . In ICML , 2014 . Ling Yan, Wu-Jun Li, Gui-Rong Xue, and Dingyi Han. Coupled group lasso for web-scale CTR prediction in display advertising. In ICML, 2014."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2019.05.006"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3151736"},{"issue":"206","key":"e_1_3_2_2_37_1","first-page":"1","article-title":"On convergence of distributed approximate Newton methods: Globalization, sharper bounds and beyond","volume":"21","author":"Yuan Xiao-Tong","year":"2020","unstructured":"Xiao-Tong Yuan and Ping Li . On convergence of distributed approximate Newton methods: Globalization, sharper bounds and beyond . Journal of Machine Learning Research , 21 ( 206 ): 1 -- 51 , 2020 . Xiao-Tong Yuan and Ping Li. On convergence of distributed approximate Newton methods: Globalization, sharper bounds and beyond. Journal of Machine Learning Research, 21(206):1--51, 2020.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_38_1","volume-title":"ICML","author":"Zhang Yuchen","year":"2015","unstructured":"Yuchen Zhang and Xiao Lin . DiSCO : Distributed optimization for self-concordant empirical loss . In ICML , 2015 . Yuchen Zhang and Xiao Lin. DiSCO: Distributed optimization for self-concordant empirical loss. In ICML, 2015."}],"event":{"name":"KDD '23: The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Long Beach CA USA","acronym":"KDD '23","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599280","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580305.3599280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:16Z","timestamp":1750182676000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580305.3599280"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,4]]},"references-count":38,"alternative-id":["10.1145\/3580305.3599280","10.1145\/3580305"],"URL":"https:\/\/doi.org\/10.1145\/3580305.3599280","relation":{},"subject":[],"published":{"date-parts":[[2023,8,4]]},"assertion":[{"value":"2023-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}