{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T19:45:45Z","timestamp":1793475945354,"version":"4.5.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T00:00:00Z","timestamp":1671235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T00:00:00Z","timestamp":1671235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,17]]},"DOI":"10.1109\/bigdata55660.2022.10020426","type":"proceedings-article","created":{"date-parts":[[2023,1,26]],"date-time":"2023-01-26T19:35:23Z","timestamp":1674761723000},"page":"1292-1297","source":"Crossref","is-referenced-by-count":6,"title":["A Convergence Theory for Federated Average: Beyond Smoothness"],"prefix":"10.1109","author":[{"given":"Xiaoxiao","family":"Li","sequence":"first","affiliation":[{"name":"UBC,Department of ECE,Vancouver,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhao","family":"Song","sequence":"additional","affiliation":[{"name":"Adobe Research Adobe,San Jose,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runzhou","family":"Tao","sequence":"additional","affiliation":[{"name":"Columbia University,Department of CS,New York,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"McGill University,Department of ECE,Montreal,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData55660.2022.10020426"},{"key":"ref2","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Artificial Intelligence and Statistics","author":"McMahan"},{"key":"ref3","article-title":"Federated optimization in heterogeneous networks","volume-title":"Conference on Machine Learning and Systems, 2020a","author":"Li"},{"key":"ref4","article-title":"On the convergence of fedavg on non-iid data","author":"Li","year":"2019"},{"key":"ref5","article-title":"First analysis of local gd on heterogeneous data","author":"Khaled","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref8","first-page":"5132","article-title":"Scaffold: Stochastic controlled averaging for federated learning","volume-title":"ICML","author":"Karimireddy"},{"key":"ref9","article-title":"Federated learning with matched averaging","author":"Wang","year":"2020"},{"key":"ref10","article-title":"Federated learning with non-iid data","author":"Zhao","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837896"},{"key":"ref12","article-title":"FedBN: Federated learning on non-IID features via local batch normalization","volume-title":"ICLR","author":"Li"},{"key":"ref13","first-page":"4423","article-title":"Fl-ntk: A neural tangent kernel-based framework for federated learning analysis","volume-title":"ICML","author":"Huang"},{"key":"ref14","article-title":"On convergence of federated averaging langevin dynamics","author":"Deng","year":"2021"},{"key":"ref15","article-title":"Iterative sketching and its application to federated learning","author":"Song","year":"2021","journal-title":"openreview"},{"key":"ref16","article-title":"Federated learning for mobile keyboard prediction","author":"Hard","year":"2018"},{"key":"ref17","article-title":"Applied federated learning: Improving google keyboard query suggestions","author":"Yang","year":"2018"},{"key":"ref18","article-title":"Federated learning for emoji prediction in a mobile keyboard","author":"Ramaswamy","year":"2019"},{"key":"ref19","article-title":"Federated learning of out-of-vocabulary words","author":"Chen","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101765"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref22","article-title":"Federated optimization: Distributed machine learning for on-device intelligence","author":"Kone\u010dn\u1ef3","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2985917"},{"key":"ref24","article-title":"Error feedback fixes signsgd and other gradient compression schemes","author":"Karimireddy","year":"2019"},{"key":"ref25","article-title":"Federated learning with additional mechanisms on clients to reduce communication costs","author":"Yao","year":"2019"},{"key":"ref26","article-title":"Federated learning with compression: Unified analysis and sharp guarantees","author":"Haddadpour","year":"2020"},{"key":"ref27","first-page":"2595","article-title":"Parallelized stochastic gradient descent","volume-title":"Advances in neural information processing systems","author":"Zinkevich"},{"key":"ref28","article-title":"Local sgd converges fast and communicates little","author":"Stich","year":"2018"},{"key":"ref29","article-title":"The error-feedback framework: Better rates for sgd with delayed gradients and compressed communication","author":"Stich","year":"2019"},{"key":"ref30","article-title":"Communication trade-offs for synchronized distributed SGD with large step size","author":"Patel","year":"2019"},{"key":"ref31","article-title":"Tighter theory for local SGD on indentical and heterogeneous data","volume-title":"Proceedings of AISTATS","author":"Khaled"},{"key":"ref32","first-page":"3556","article-title":"Local sgd: Unified theory and new efficient methods","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Gorbunov"},{"key":"ref33","first-page":"5381","article-title":"A unified theory of decentralized sgd with changing topology and local updates","volume-title":"ICML","author":"Koloskova"},{"key":"ref34","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","volume-title":"ICML","author":"Allen-Zhu"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/030601296"},{"key":"ref36","first-page":"597","article-title":"Convergence analysis of two-layer neural networks with ReLU activation","volume-title":"NeurIPS","author":"Li"}],"event":{"name":"2022 IEEE International Conference on Big Data (Big Data)","location":"Osaka, Japan","start":{"date-parts":[[2022,12,17]]},"end":{"date-parts":[[2022,12,20]]}},"container-title":["2022 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10020192\/10020156\/10020426.pdf?arnumber=10020426","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:34:53Z","timestamp":1707806093000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10020426\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,17]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/bigdata55660.2022.10020426","relation":{},"subject":[],"published":{"date-parts":[[2022,12,17]]}}}