{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:07:09Z","timestamp":1772039229363,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Wallenberg Artificial Intelligence, Autonomous Systems and Software Program"},{"DOI":"10.13039\/501100004359","name":"Vetenskapsr\u00e5det","doi-asserted-by":"publisher","award":["2020-03607"],"award-info":[{"award-number":["2020-03607"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tsp.2023.3237392","type":"journal-article","created":{"date-parts":[[2023,1,26]],"date-time":"2023-01-26T18:53:51Z","timestamp":1674759231000},"page":"189-201","source":"Crossref","is-referenced-by-count":9,"title":["Improved Step-Size Schedules for Proximal Noisy Gradient Methods"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4473-2011","authenticated-orcid":false,"given":"Sarit","family":"Khirirat","sequence":"first","affiliation":[{"name":"Division of Decision and Control Systems, Royal Institute of Technology (KTH), Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4102-4909","authenticated-orcid":false,"given":"Xiaoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Division of Decision and Control Systems, Royal Institute of Technology (KTH), Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6617-8683","authenticated-orcid":false,"given":"Sindri","family":"Magn\u00fasson","sequence":"additional","affiliation":[{"name":"Department of Computer and System Science, Stockholm University, Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mikael","family":"Johansson","sequence":"additional","affiliation":[{"name":"Division of Decision and Control Systems, Royal Institute of Technology (KTH), Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414419"},{"key":"ref2","volume-title":"Introduction to Optimization","author":"Polyak","year":"1987"},{"key":"ref3","first-page":"451","article-title":"Non-asymptotic analysis of stochastic approximation algorithms for machine learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Moulines","year":"2011"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref6","first-page":"1571","article-title":"Making gradient descent optimal for strongly convex stochastic optimization","volume-title":"Proc. 29th Int. Conf. Int. Conf. Mach. Learn.","author":"Rakhlin","year":"2012"},{"key":"ref7","article-title":"A simpler approach to obtaining an $\\mathcal {O}(1\/t)$ convergence rate for the projected stochastic subgradient method","author":"Lacoste-Julien","year":"2012"},{"key":"ref8","first-page":"71","article-title":"Stochastic gradient descent for non-smooth optimization: Convergence results and optimal averaging schemes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shamir","year":"2013"},{"key":"ref9","first-page":"5200","article-title":"SGD: General analysis and improved rates","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gower","year":"2019"},{"key":"ref10","first-page":"3750","article-title":"SGD and hogwild! Convergence without the bounded gradients assumption","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nguyen","year":"2018"},{"key":"ref11","article-title":"On the convergence rate of stochastic mirror descent for nonsmooth nonconvex optimization","author":"Zhang","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s00245-019-09617-7"},{"key":"ref13","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alistarh","year":"2017"},{"key":"ref14","first-page":"560","article-title":"signSGD: Compressed optimisation for non-convex problems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bernstein","year":"2018"},{"key":"ref15","article-title":"Optimal gradient compression for distributed and federated learning","author":"Albasyoni","year":"2020"},{"key":"ref16","first-page":"1509","article-title":"Terngrad: Ternary gradients to reduce communication in distributed deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2743678"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF44664.2019.9049052"},{"key":"ref19","first-page":"3368","article-title":"Gradient coding: Avoiding stragglers in distributed learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tandon","year":"2017"},{"issue":"1","key":"ref20","first-page":"2619","article-title":"Redundancy techniques for straggler mitigation in distributed optimization and learning","volume":"20","author":"Karakus","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","first-page":"5610","article-title":"Communication-computation efficient gradient coding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ye","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/120880811"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-8991-9_29"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-023-02297-y"},{"key":"ref28","first-page":"3935","article-title":"Almost sure convergence rates for stochastic gradient descent and stochastic heavy ball","volume-title":"Proc. Conf. Learn. Theory","author":"Sebbouh","year":"2021"},{"key":"ref29","first-page":"1299","article-title":"Gradient sparsification for communication-efficient distributed optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wangni","year":"2018"},{"key":"ref30","first-page":"9850","article-title":"ATOMO: Communication-efficient learning via atomic sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16987"},{"key":"ref32","article-title":"Distributed learning with compressed gradients","author":"Khirirat","year":"2018"},{"key":"ref33","first-page":"3478","article-title":"Decentralized stochastic optimization and gossip algorithms with compressed communication","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koloskova","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2991361"},{"key":"ref35","article-title":"Hessian-aware zeroth-order optimization for black-box adversarial attack","author":"Ye","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10589-021-00313-3"},{"issue":"3","key":"ref37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1961189.1961199","article-title":"LIBSVM: A library for support vector machines","volume":"2","author":"Chang","year":"2011","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-019-01405-z"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2307\/1267936"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1137\/18M1178244"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/78\/10040758\/10026503.pdf?arnumber=10026503","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T06:03:10Z","timestamp":1712901790000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10026503\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/tsp.2023.3237392","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}