{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T18:10:19Z","timestamp":1749492619662,"version":"3.41.0"},"reference-count":68,"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":[{"name":"NSF China","award":["62373388"],"award-info":[{"award-number":["62373388"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tsp.2025.3569665","type":"journal-article","created":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T17:34:46Z","timestamp":1747244086000},"page":"1939-1953","source":"Crossref","is-referenced-by-count":0,"title":["Single-Timescale Multi-Sequence Stochastic Approximation Without Fixed Point Smoothness: Theories and Applications"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2120-8016","authenticated-orcid":false,"given":"Yue","family":"Huang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering and Guangdong Provincial Key Laboratory of Computational Science, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6724-6134","authenticated-orcid":false,"given":"Zhaoxian","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering and Guangdong Provincial Key Laboratory of Computational Science, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1967-1069","authenticated-orcid":false,"given":"Shiqian","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Computational Applied Mathematics and Operations Research, Rice University, Houston, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4222-5964","authenticated-orcid":false,"given":"Qing","family":"Ling","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering and Guangdong Provincial Key Laboratory of Computational Science, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s12045-013-0136-x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3301121"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref7","article-title":"A single-timescale analysis for stochastic approximation with multiple coupled sequences","volume-title":"Proc. NeurIPS","author":"Shen","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/18M1164846"},{"key":"ref9","article-title":"A gradient method for multilevel optimization","volume-title":"Proc. NeurIPS","author":"Sato","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414369"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3092377"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/10556788.2024.2358790"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1977.1101561"},{"volume-title":"Stochastic Approximation and Recursive Algorithms and Applications","year":"2003","author":"Kushner","key":"ref14"},{"key":"ref15","first-page":"451","article-title":"Non-asymptotic analysis of stochastic approximation algorithms for machine learning","author":"Moulines","year":"2011","journal-title":"Proc. NeurIPS"},{"key":"ref16","first-page":"1691","article-title":"A finite time analysis of temporal difference learning with linear function approximation","author":"Bhandari","year":"2018","journal-title":"Proc. COLT"},{"key":"ref17","first-page":"8223","article-title":"Finite-sample analysis of contractive stochastic approximation using smooth convex envelopes","author":"Chen","year":"2020","journal-title":"Proc. NeurIPS"},{"key":"ref18","first-page":"2144","article-title":"Finite time analysis of linear two-timescale stochastic approximation with Markovian noise","author":"Kaledin","year":"2020","journal-title":"Proc. COLT"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1214\/105051606000000448"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3210147"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1137\/20M1387341"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1137\/22M150277X"},{"article-title":"Finite-time decoupled convergence in nonlinear two-time-scale stochastic approximation","year":"2024","author":"Han","key":"ref23"},{"article-title":"Fast nonlinear two-time-scale stochastic approximation: Achieving $\\mathcal{O}(1\/k)$ finite-sample complexity","year":"2024","author":"Doan","key":"ref24"},{"article-title":"$n$-timescale stochastic approximation: Stability and convergence","year":"2021","author":"Deb","key":"ref25"},{"article-title":"Accelerated multi-time-scale stochastic approximation: Optimal complexity and applications in reinforcement learning and multi-agent games","year":"2024","author":"Zeng","key":"ref26"},{"key":"ref27","first-page":"26698","article-title":"A framework for bilevel optimization that enables stochastic and global variance reduction algorithms","volume-title":"Proc. NeurIPS","author":"Dagr\u00e9ou","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447185"},{"key":"ref29","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. NeurIPS","author":"Konda","year":"1999"},{"key":"ref30","first-page":"1944","article-title":"Non-asymptotic analysis of biased stochastic approximation scheme","volume-title":"Proc. COLT","author":"Karimi","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1137\/120880811"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095940"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414206"},{"key":"ref35","first-page":"4882","article-title":"Bilevel optimization: Convergence analysis and enhanced design","author":"Ji","year":"2021","journal-title":"Proc. ICML"},{"key":"ref36","first-page":"737","article-title":"Hyperparameter optimization with approximate gradient","author":"Pedregosa","year":"2016","journal-title":"Proc. ICML"},{"key":"ref37","first-page":"3748","article-title":"On the iteration complexity of hypergradient computation","author":"Grazzi","year":"2020","journal-title":"Proc. ICML"},{"key":"ref38","first-page":"1568","article-title":"Bilevel programming for hyperparameter optimization and meta-learning","author":"Franceschi","year":"2018","journal-title":"Proc. ICML"},{"key":"ref39","first-page":"1723","article-title":"Truncated back-propagation for bilevel optimization","volume-title":"Proc. AISTATS","author":"Shaban","year":"2019"},{"article-title":"Approximation methods for bilevel programming","year":"2018","author":"Ghadimi","key":"ref40"},{"key":"ref41","first-page":"25294","article-title":"Closing the gap: Tighter analysis of alternating stochastic gradient methods for bilevel problems","volume-title":"Proc. NeurIPS","author":"Chen","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3234462"},{"issue":"151","key":"ref43","first-page":"1","article-title":"Optimal algorithms for stochastic bilevel optimization under relaxed smoothness conditions","volume":"25","author":"Chen","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20706"},{"key":"ref45","first-page":"1","article-title":"Local SGD converges fast and communicates little","volume-title":"Proc. ICLR","author":"Stich","year":"2019"},{"key":"ref46","first-page":"1","article-title":"On the convergence of FEDAVG on non-IID data","volume-title":"Proc. ICLR","author":"Li","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(64)90137-5"},{"key":"ref48","first-page":"11450","article-title":"Communication-efficient distributed blockwise momentum SGD with error-feedback","author":"Zheng","year":"2019","journal-title":"Proc. NeurIPS"},{"key":"ref49","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization","volume-title":"Proc. ICML","author":"Yu","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.2975189"},{"key":"ref51","first-page":"1707","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume-title":"Proc. NeurIPS","author":"Alistarh","year":"2017"},{"key":"ref52","first-page":"1","article-title":"Mixed precision training","author":"Micikevicius","year":"2018","journal-title":"Proc. ICLR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3031073"},{"key":"ref54","first-page":"4452","article-title":"Sparsified SGD with memory","volume-title":"Proc. NeurIPS","author":"Stich","year":"2018"},{"key":"ref55","first-page":"1306","article-title":"Gradient sparsification for communication-efficient distributed optimization","volume-title":"Proc. NeurIPS","author":"Wangni","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaab006"},{"key":"ref57","first-page":"30401","article-title":"Error compensated distributed SGD can be accelerated","volume-title":"Proc. NeurIPS","author":"Qian","year":"2021"},{"key":"ref58","first-page":"47991","article-title":"Unbiased compression saves communication in distributed optimization: When and how much?","volume-title":"Proc. NeurIPS","author":"He","year":"2024"},{"article-title":"Lower bounds and accelerated algorithms in distributed stochastic optimization with communication compression","year":"2023","author":"He","key":"ref59"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3385577"},{"article-title":"On communication compression for distributed optimization on heterogeneous data","year":"2020","author":"Stich","key":"ref61"},{"key":"ref62","first-page":"1","article-title":"Information-theoretic lower bounds on the oracle complexity of convex optimization","volume-title":"Proc. NeurIPS","author":"Agarwal","year":"2009"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-022-01822-7"},{"key":"ref64","first-page":"1","article-title":"SlowMo: Improving communication-efficient distributed SGD with slow momentum","author":"Wang","year":"2020","journal-title":"Proc. ICLR"},{"key":"ref65","first-page":"9965","article-title":"Towards understanding how momentum improves generalization in deep learning","author":"Jelassi","year":"2022","journal-title":"Proc. ICML"},{"key":"ref66","first-page":"1","article-title":"Momentum benefits non-iid federated learning simply and provably","author":"Cheng","year":"2024","journal-title":"Proc. ICLR"},{"key":"ref67","first-page":"1165","article-title":"Forward and reverse gradient-based hyperparameter optimization","author":"Franceschi","year":"2017","journal-title":"Proc. ICML"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447185"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/10807692\/11003478.pdf?arnumber=11003478","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T17:37:10Z","timestamp":1749490630000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11003478\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tsp.2025.3569665","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"type":"print","value":"1053-587X"},{"type":"electronic","value":"1941-0476"}],"subject":[],"published":{"date-parts":[[2025]]}}}