{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:03:49Z","timestamp":1770746629786,"version":"3.49.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["92370121"],"award-info":[{"award-number":["92370121"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["12301392"],"award-info":[{"award-number":["12301392"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["124B2017"],"award-info":[{"award-number":["124B2017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["W2441021"],"award-info":[{"award-number":["W2441021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["8200907251"],"award-info":[{"award-number":["8200907251"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tsp.2025.3644008","type":"journal-article","created":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T18:40:40Z","timestamp":1765824040000},"page":"340-354","source":"Crossref","is-referenced-by-count":0,"title":["A Convergence-Motivated Learning-to-Optimize Framework for Decentralized Optimization"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5078-6454","authenticated-orcid":false,"given":"Yutong","family":"He","sequence":"first","affiliation":[{"name":"Center for Data Science, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5727-9185","authenticated-orcid":false,"given":"Qiulin","family":"Shang","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering and Computer Science, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4632-4188","authenticated-orcid":false,"given":"Xinmeng","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0861-1856","authenticated-orcid":false,"given":"Jialin","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Statistics and Data Science, University of Central Florida, Orlando, FL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8394-8187","authenticated-orcid":false,"given":"Kun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Center for Machine Learning Research, Peking University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2024.3516564"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/130943170"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2008.917383"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2012.2198470"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2161027"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2304432"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/14096668X"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2875898"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2926022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1137\/16M1084316"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2015.7402509"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2016.2524588"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104374"},{"key":"ref15","first-page":"3981","article-title":"Learning to learn by gradient descent by gradient descent","volume":"29","author":"Andrychowicz","year":"2016","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.07.063"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3016905"},{"issue":"1","key":"ref18","first-page":"8562","article-title":"Learning to optimize: A primer and a benchmark","volume":"23","author":"Chen","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref19","first-page":"2247","article-title":"Learning gradient descent: Better generalization and longer horizons","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lv","year":"2017"},{"key":"ref20","first-page":"3751","article-title":"Learned optimizers that scale and generalize","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wichrowska","year":"2017"},{"key":"ref21","article-title":"Understanding short-horizon bias in stochastic meta-optimization","author":"Wu","year":"2018"},{"key":"ref22","first-page":"4556","article-title":"Understanding and correcting pathologies in the training of learned optimizers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Metz","year":"2019"},{"key":"ref23","first-page":"7332","article-title":"Training stronger baselines for learning to optimize","volume":"33","author":"Chen","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref24","first-page":"10798","article-title":"Gradient-based hyperparameter optimization over long horizons","volume":"34","author":"Micaelli","year":"2021","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref25","article-title":"VeLO: Training versatile learned optimizers by scaling up","author":"Metz","year":"2022"},{"key":"ref26","article-title":"Towards constituting mathematical structures for learning to optimize","author":"Liu","year":"2023"},{"key":"ref27","first-page":"2262","article-title":"Understanding trainable sparse coding via matrix factorization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Moreau","year":"2017"},{"key":"ref28","first-page":"9061","article-title":"Theoretical linear convergence of unfolded ISTA and its practical weights and thresholds","volume":"31","author":"Chen","year":"2018","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref29","article-title":"ALISTA: Analytic weights are as good as learned weights in LISTA","volume-title":"Int. Conf. Learn. Representations (ICLR)","author":"Liu","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2912879"},{"key":"ref31","first-page":"10","article-title":"Deep ADMM-Net for compressive sensing MRI","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Yang","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00196"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2799231"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2941271"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9682857"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2461520"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2013.6737048"},{"key":"ref39","first-page":"9613","article-title":"Learning a minimax optimizer: A pilot study","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Shen","year":"2021"},{"key":"ref40","article-title":"A closer look at learned optimization: Stability, robustness, and inductive biases","author":"Harrison","year":"2022"},{"key":"ref41","first-page":"1","article-title":"Learned optimizers that outperform SGD on wall-clock and test loss","volume-title":"Proc. 2nd Workshop Meta-Learn. (MetaLearn)","volume":"2019","author":"Metz","year":"2018"},{"key":"ref42","first-page":"142","article-title":"Practical tradeoffs between memory, compute, and performance in learned optimizers","volume-title":"Proc. Conf. Lifelong Learn. Agents","author":"Metz","year":"2022"},{"key":"ref43","article-title":"Mnemosyne: Learning to train transformers with transformers","volume":"36","author":"Jain","year":"2023","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref44","first-page":"5330","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","volume":"30","author":"Lian","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2872003"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3009363"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3086579"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3014148"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2021-Fall52928.2021.9625549"},{"key":"ref50","article-title":"Limited communications distributed optimization via deep unfolded distributed ADMM","author":"Noah","year":"2023"},{"key":"ref51","article-title":"Stochastic unrolled federated learning","author":"Hadou","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tcns.2025.3587331"},{"key":"ref53","first-page":"748","article-title":"Learning to learn without gradient descent by gradient descent","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2017"},{"key":"ref54","article-title":"Learning to optimize in swarms","volume":"32","author":"Cao","year":"2019","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref55","article-title":"RNA secondary structure prediction by learning unrolled algorithms","author":"Chen","year":"2020"},{"key":"ref56","first-page":"1520","article-title":"Learning to stop while learning to predict","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref57","first-page":"18308","article-title":"Decentralized accelerated proximal gradient descent","volume":"33","author":"Ye","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref58","article-title":"Optimal decentralized composite optimization for strongly convex functions","author":"Ye","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref61","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.881199"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.355\/supp-1"},{"key":"ref64","article-title":"Problem-parameter-free decentralized nonconvex stochastic optimization","author":"Li","year":"2024"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3223214"},{"key":"ref66","first-page":"96011","article-title":"Achieving linear convergence with parameter-free algorithms in decentralized optimization","volume-title":"Proc. 38th Annu. Conf. Neural Inf. Process. Syst","volume":"2024","author":"Kuruzov"},{"key":"ref67","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Hsu","year":"2019"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1137\/S0036144503423264"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/11345506\/11299607.pdf?arnumber=11299607","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T05:56:27Z","timestamp":1770702987000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11299607\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/tsp.2025.3644008","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}