{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:38:38Z","timestamp":1779295118437,"version":"3.51.4"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSAF","doi-asserted-by":"publisher","award":["U2230201"],"award-info":[{"award-number":["U2230201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tsp.2025.3528217","type":"journal-article","created":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T21:02:42Z","timestamp":1736542962000},"page":"462-476","source":"Crossref","is-referenced-by-count":4,"title":["Adaptive Polyak Step-Size for Momentum Accelerated Stochastic Gradient Descent With General Convergence Guarantee"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0083-2584","authenticated-orcid":false,"given":"Jiawei","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4798-1787","authenticated-orcid":false,"given":"Cheng","family":"Jin","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8427-1021","authenticated-orcid":false,"given":"Yuantao","family":"Gu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8660-3"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2301135"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1982.12433"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2010.2057247"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref6","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref7","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Johnson","year":"2013"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref9","first-page":"3935","article-title":"Almost sure convergence rates for stochastic gradient descent and stochastic heavy ball","volume-title":"Proc. 34th Conf. Learn. Theory","volume":"134","author":"Sebbouh","year":"2021"},{"key":"ref10","first-page":"18261","article-title":"An improved analysis of stochastic gradient descent with momentum","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Liu","year":"2020"},{"key":"ref11","first-page":"36559","article-title":"Revisit last-iterate convergence of MSGD under milder requirement on step size","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Jin","year":"2022"},{"key":"ref12","first-page":"1","article-title":"On the convergence of mSGD and AdaGrad for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jin","year":"2022"},{"key":"ref13","first-page":"2963","article-title":"On almost sure convergence rates of stochastic gradient methods","volume-title":"Proc. 35th Conf. Learn. Theory","volume":"178","author":"Liu","year":"2022"},{"key":"ref14","first-page":"699","article-title":"On the last iterate convergence of momentum methods","volume-title":"Proc. Int. Conf. Algorithmic Learn. Theory","author":"Li","year":"2022"},{"issue":"2","key":"ref15","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky","year":"2012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026899"},{"key":"ref19","first-page":"2019","article-title":"PYTORCH: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref20","first-page":"1","article-title":"ADAM: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Diederik","year":"2015"},{"key":"ref21","first-page":"6434","article-title":"L4: Practical loss-based stepsize adaptation for deep learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Rolinek","year":"2018"},{"key":"ref22","first-page":"799","article-title":"Training neural networks for and by interpolation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Berrada","year":"2020"},{"key":"ref23","first-page":"2019","article-title":"Painless stochastic gradient: Interpolation, line-search, and convergence rates","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Vaswani"},{"key":"ref24","first-page":"1306","article-title":"Stochastic Polyak step-size for SGD: An adaptive learning rate for fast convergence","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Loizou","year":"2021"},{"key":"ref25","article-title":"Introduction to optimization. Translations series in mathematics and engineering","author":"Polyak","year":"1987"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-021-01628-3"},{"key":"ref27","article-title":"Adaptive learning rates for faster stochastic gradient methods","author":"Horv\u00e1th","year":"2022"},{"key":"ref28","first-page":"1","article-title":"SP2: A second order stochastic Polyak method","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2023"},{"key":"ref29","article-title":"Cutting some slack for SGD with adaptive Polyak stepsizes","author":"Gower","year":"2022"},{"key":"ref30","first-page":"35836","article-title":"Generalized Polyak step size for first order optimization with momentum","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2023"},{"key":"ref31","article-title":"Stochastic Polyak step-sizes and momentum: Convergence guarantees and practical performance","author":"Oikonomou","year":"2024"},{"key":"ref32","first-page":"26943","article-title":"Dynamics of sgd with stochastic polyak stepsizes: Truly adaptive variants and convergence to exact solution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Orvieto","year":"2022"},{"key":"ref33","first-page":"1","article-title":"A stochastic proximal polyak step size","volume":"2023","author":"Schaipp","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref34","first-page":"1","article-title":"On stochastic mirror descent: Convergence analysis and adaptive variants","volume-title":"Proc. Beyond 1st-Order Methods ML Syst. Workshop, Int. Conf. Mach. Learn.","author":"D\u2019Orazio","year":"2021"},{"key":"ref35","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":"ref36","first-page":"1","article-title":"On the variance of the adaptive learning rate and beyond","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2020"},{"key":"ref37","first-page":"1","article-title":"Adaptive gradient methods with dynamic bound of learning rate","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Luo","year":"2019"},{"key":"ref38","first-page":"15236","article-title":"Momentum-based variance reduction in non-convex SGD","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Cutkosky","year":"2019"},{"key":"ref39","first-page":"2019","article-title":"Lookahead optimizer: K steps forward, 1 step back","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zhang"},{"key":"ref40","first-page":"685","article-title":"Barzilai-Borwein step size for stochastic gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Tan","year":"2016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91578-4"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/10807692\/10836899.pdf?arnumber=10836899","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T18:54:03Z","timestamp":1738090443000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10836899\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/tsp.2025.3528217","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}