{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T17:19:00Z","timestamp":1769879940063,"version":"3.49.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2047177"],"award-info":[{"award-number":["2047177"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"RPI-IBM Artificial Intelligence Research Collaboration"},{"name":"ONR","award":["N000141712162"],"award-info":[{"award-number":["N000141712162"]}]},{"name":"AFOSR MURI","award":["FA9550-18-1-0502"],"award-info":[{"award-number":["FA9550-18-1-0502"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tsp.2021.3092377","type":"journal-article","created":{"date-parts":[[2021,6,28]],"date-time":"2021-06-28T20:31:41Z","timestamp":1624912301000},"page":"4937-4948","source":"Crossref","is-referenced-by-count":34,"title":["Solving Stochastic Compositional Optimization is Nearly as Easy as Solving Stochastic Optimization"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3477-1439","authenticated-orcid":false,"given":"Tianyi","family":"Chen","sequence":"first","affiliation":[]},{"given":"Yuejiao","family":"Sun","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6697-9731","authenticated-orcid":false,"given":"Wotao","family":"Yin","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"On the convergence of a class of adam-type algorithms for non-convex optimization","author":"chen","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref38","article-title":"On the convergence of adam and beyond","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref33","article-title":"Optimization as a model for few-shot learning","author":"ravi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref32","article-title":"Provably convergent policy gradient methods for model-agnostic meta-reinforcement learning","author":"fallah","year":"2020"},{"key":"ref31","article-title":"ES-MAML: Simple hessian-free meta learning","author":"song","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref30","first-page":"424","article-title":"Provable guarantees for gradient-based meta-learning","author":"khodak","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref36","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref34","article-title":"Multi-step model-agnostic meta-learning: Convergence and improved algorithms","year":"0","journal-title":"J Mach Learn Res"},{"key":"ref10","first-page":"7454","article-title":"A composite randomized incremental gradient method","author":"zhang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1137\/120880811"},{"key":"ref11","first-page":"9075","article-title":"A stochastic composite gradient method with incremental variance reduction","author":"zhang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1137\/20M1312952"},{"key":"ref13","first-page":"1159","article-title":"Finite-sum composition optimization via variance reduced gradient descent","author":"lian","year":"0","journal-title":"Proc Int Conf Artif Intell Stat"},{"key":"ref14","first-page":"315","article-title":"Accelerating stochastic gradient descent using predictive variance reduction","author":"johnson","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","first-page":"1646","article-title":"SAGA: A fast incremental gradient method with support for non-strongly convex composite objectives","author":"defazio","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"2613","article-title":"SARAH: A novel method for machine learning problems using stochastic recursive gradient","author":"nguyen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","first-page":"689","article-title":"SPIDER: Near-optimal non-convex optimization via stochastic path-integrated differential estimator","author":"fang","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","first-page":"3921","article-title":"Stochastic nested variance reduction for nonconvex optimization","volume":"31","author":"zhou","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","article-title":"Unbiased simulation for optimizing stochastic function compositions","author":"blanchet","year":"2017"},{"key":"ref28","article-title":"On first-order meta-learning algorithms","author":"nichol","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718751"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/6GSUMMIT49458.2020.9083856"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-1017-3"},{"key":"ref6","first-page":"3721","article-title":"Accelerating stochastic composition optimization","volume":"18","author":"wang","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref29","article-title":"On the convergence theory of gradient-based model-agnostic meta-learning algorithms","author":"fallah","year":"0","journal-title":"Proc Int Conf Artificial Intell Stat"},{"key":"ref5","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/18M1230542"},{"key":"ref7","article-title":"Compositional adam: An adaptive compositional solver","author":"tutunov","year":"2020"},{"key":"ref2","first-page":"809","article-title":"Policy evaluation with temporal differences: A survey and comparison","volume":"15","author":"dann","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref9","first-page":"6926","article-title":"Efficient smooth non-convex stochastic compositional optimization via stochastic recursive gradient descent","author":"hu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref20","first-page":"9878","article-title":"Stochastic variance reduced primal dual algorithms for empirical composition optimization","author":"devraj","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","article-title":"Accelerated method for stochastic composition optimization with nonsmooth regularization","year":"0","journal-title":"Proc Assoc Adv Artif Intell"},{"key":"ref21","article-title":"Improved oracle complexity for stochastic compositional variance reduced gradient","author":"lin","year":"0","journal-title":"Proc Amer Control Conf Virtual"},{"key":"ref24","article-title":"Katyusha acceleration for convex finite-sum compositional optimization","author":"xu","year":"2019"},{"key":"ref41","article-title":"Solving stochastic compositional optimization is nearly as easy as solving stochastic optimization","author":"chen","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/470"},{"key":"ref26","first-page":"4061","article-title":"Taming maml: Efficient unbiased meta-reinforcement learning","author":"liu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","first-page":"1920","article-title":"Online meta-learning","author":"finn","year":"0","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/78\/9307529\/9465746-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/78\/9307529\/09465746.pdf?arnumber=9465746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:45Z","timestamp":1652194245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9465746\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/tsp.2021.3092377","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}