{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T06:16:47Z","timestamp":1769062607152,"version":"3.49.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"DST project","award":["MTR\/2019\/000181"],"award-info":[{"award-number":["MTR\/2019\/000181"]}]},{"name":"Army Cooperative Agreement","award":["W911NF2120076"],"award-info":[{"award-number":["W911NF2120076"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tsp.2023.3234462","type":"journal-article","created":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T18:42:47Z","timestamp":1674240167000},"page":"6332-6347","source":"Crossref","is-referenced-by-count":9,"title":["Projection-Free Stochastic Bi-Level Optimization"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1509-7899","authenticated-orcid":false,"given":"Zeeshan","family":"Akhtar","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering, Indian Institute of Technology Kanpur, Kanpur, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8807-2695","authenticated-orcid":false,"given":"Amrit Singh","family":"Bedi","sequence":"additional","affiliation":[{"name":"Institute of Systems Research, University of Maryland, College Park, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5837-2999","authenticated-orcid":false,"given":"Srujan Teja","family":"Thomdapu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Indian Institute of Technology Kanpur, Kanpur, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4508-0062","authenticated-orcid":false,"given":"Ketan","family":"Rajawat","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Indian Institute of Technology Kanpur, Kanpur, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"113","article-title":"Meta-learning with implicit gradients","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Rajeswaran","year":"2019"},{"key":"ref2","first-page":"14879","article-title":"Coresets via bilevel optimization for continual learning and streaming","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Borsos","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6226"},{"key":"ref4","first-page":"1568","article-title":"Bilevel programming for hyperparameter optimization and meta-learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Franceschi","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1137\/20m1387341"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-52119-6"},{"key":"ref7","article-title":"Approximation methods for bilevel programming","author":"Ghadimi","year":"2018"},{"key":"ref8","first-page":"13670","article-title":"Provably faster algorithms for bilevel optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref9","first-page":"2466","article-title":"A single-timescale method for stochastic bilevel optimization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist., PMLR","author":"Chen","year":"2022"},{"key":"ref10","first-page":"30271","article-title":"A near-optimal algorithm for stochastic bilevel optimization via double-momentum","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Khanduri","year":"2021"},{"key":"ref11","first-page":"25294","article-title":"Closing the gap: Tighter analysis of alternating stochastic gradient method for stochastic nested problems","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen","year":"2021"},{"key":"ref12","first-page":"427","article-title":"Revisiting Frank-Wolfe: Projection-free sparse convex optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaggi","year":"2013"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800030109"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-1017-3"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/18M1230542"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3092377"},{"issue":"105","key":"ref17","first-page":"1","article-title":"Stochastic conditional gradient methods: From convex minimization to submodular maximization","volume":"21","author":"Mokhtari","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6116"},{"key":"ref19","first-page":"4012","article-title":"One sample stochastic Frank-Wolfe","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Zhang","year":"2020"},{"key":"ref20","first-page":"1722","article-title":"Accelerating stochastic composition optimization","author":"Wang","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","first-page":"4882","article-title":"Bilevel optimization: Convergence analysis and enhanced design","volume-title":"Proc. Int. Conf. Mach. Learn., PMLR","author":"Ji","year":"2021"},{"key":"ref22","first-page":"30 271","article-title":"A near-optimal algorithm for stochastic bilevel optimization via double- momentum","volume":"34","author":"Khanduri","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3162958"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2488608.2488693"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2941319"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0010"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553454"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.409"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaaa020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539849"},{"key":"ref31","article-title":"Matrix completion from noisy entries","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"22","author":"Keshavan","year":"2009"},{"key":"ref32","article-title":"Supervised learning of sparsity-promoting regularizers for denoising","author":"McCann","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506489"},{"key":"ref34","first-page":"11909","article-title":"Addressing catastrophic forgetting in few-shot problems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yap","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.2307\/2550609"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68860-0_2"},{"key":"ref37","article-title":"BiAdam: Fast adaptive bilevel optimization methods","author":"Huang","year":"2021"},{"key":"ref38","article-title":"Enhanced bilevel optimization via bregman distance","author":"Huang","year":"2021"},{"key":"ref39","first-page":"15236","article-title":"Momentum-based variance reduction in non-convex SGD","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Cutkosky","year":"2019"},{"key":"ref40","first-page":"1159","article-title":"Finite-sum composition optimization via variance reduced gradient descent","volume-title":"Proc. Artif. Intell. Statist.","author":"Lian","year":"2017"},{"key":"ref41","first-page":"9078","article-title":"A stochastic composite gradient method with incremental variance reduction","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Zhang","year":"2019"},{"key":"ref42","article-title":"A framework for bilevel optimization that enables stochastic and global variance reduction algorithms","author":"Dagrou","year":"2022"},{"key":"ref43","first-page":"1646","article-title":"SAGA: A fast incremental gradient method with support for non-strongly convex composite objectives","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Defazio","year":"2014"},{"key":"ref44","article-title":"Stochastic recursive variance reduction for efficient smooth non-convex compositional optimization","author":"Yuan","year":"2019"},{"key":"ref45","article-title":"Stochastic recursive momentum method for non-convex compositional optimization","author":"Yang","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tsp.2023.3244326"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3071594"},{"key":"ref48","first-page":"6929","article-title":"Efficient smooth non-convex stochastic compositional optimization via stochastic recursive gradient descent","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Yuan","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"ref50","first-page":"1574","article-title":"Stochastic proximal gradient descent with acceleration techniques","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Nitanda","year":"2014"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-010-0434-y"},{"key":"ref52","first-page":"1263","article-title":"Variance-reduced and projection-free stochastic optimization","volume-title":"Proc. nt. Conf. Mach. Learn.","author":"Hazan","year":"2016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2016.7852377"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1137\/19M1304271"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974997"},{"key":"ref56","article-title":"Convergence rate of Frank-Wolfe for non-convex objectives","author":"Lacoste-Julien","year":"2016"},{"key":"ref57","first-page":"494","article-title":"Investigating practical linear temporal difference learning","volume-title":"Proc. Int. Conf. Auton. Agents & Multiagent Syst.","author":"White","year":"2016"},{"key":"ref58","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1007\/s10107-015-0946-6","article-title":"Fast projection onto the simplex and the l1 ball","volume":"158","author":"Laurent","year":"2016","journal-title":"Math. Prog"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/78\/9675017\/10023994.pdf?arnumber=10023994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:45:23Z","timestamp":1707806723000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023994\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tsp.2023.3234462","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}