{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:37:00Z","timestamp":1777736220889,"version":"3.51.4"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tac.2023.3328510","type":"journal-article","created":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T19:46:40Z","timestamp":1698695200000},"page":"2281-2293","source":"Crossref","is-referenced-by-count":6,"title":["Generalized Gradient Flows With Provable Fixed-Time Convergence and Fast Evasion of Non-Degenerate Saddle Points"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9354-2826","authenticated-orcid":false,"given":"Mayank","family":"Baranwal","sequence":"first","affiliation":[{"name":"Tata Consultancy Services Research, Mumbai, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4311-391X","authenticated-orcid":false,"given":"Param","family":"Budhraja","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Boston University, Boston, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4315-9918","authenticated-orcid":false,"given":"Vishal","family":"Raj","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Indian Institute of Technology, Kharagpur, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0562-0594","authenticated-orcid":false,"given":"Ashish R.","family":"Hota","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Indian Institute of Technology, Kharagpur, India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974997"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(64)90137-5"},{"key":"ref4","first-page":"543","article-title":"A method for unconstrained convex minimization problem with the rate of convergence $o(1\/k^{2})$","volume":"269","author":"Nesterov","year":"1983","journal-title":"Dokl. Akad. Nauk. SSSR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3007634"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1614734113"},{"issue":"17","key":"ref7","first-page":"1","article-title":"Continuous time analysis of momentum methods","volume":"22","author":"Kovachki","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","volume-title":"Nonlinear Systems","author":"Khalil","year":"2002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/15M1009597"},{"key":"ref10","first-page":"1087","article-title":"Accelerated stochastic mirror descent: From continuous-time dynamics to discrete-time algorithms","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Xu","year":"2018"},{"key":"ref11","article-title":"Continuous-time models for stochastic optimization algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Orvieto","year":"2019"},{"key":"ref12","first-page":"8200","article-title":"Finite-time convergence in continuous-time optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Romero","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20559"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997321358"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.06.015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2179869"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3001436"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46128-1_50"},{"key":"ref19","first-page":"7937","article-title":"Proxy convexity: A unified framework for the analysis of neural networks trained by gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Frei","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2021.12.009"},{"key":"ref21","article-title":"Gradient descent provably optimizes over-parameterized neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Du","year":"2019"},{"key":"ref22","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Allen-Zhu","year":"2019"},{"key":"ref23","article-title":"The power of normalization: Faster evasion of saddle points","author":"Levy","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2914998"},{"key":"ref25","article-title":"Accelerating rescaled gradient descent: Fast optimization of smooth functions","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Wilson","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"issue":"7","key":"ref28","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":"ref29","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2016"},{"key":"ref30","volume-title":"Introductory Lectures on Convex Optimization: A Basic Course","volume":"87","author":"Nesterov","year":"2003"},{"key":"ref31","article-title":"Identifying and attacking the saddle point problem in high-dimensional non-convex optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Dauphin","year":"2014"},{"key":"ref32","first-page":"1246","article-title":"Gradient descent only converges to minimizers","volume-title":"Proc. 29th Annu. Conf. Learn. Theory","author":"Lee","year":"2016"},{"key":"ref33","first-page":"1067","article-title":"Gradient descent can take exponential time to escape saddle points","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Du","year":"2017"},{"key":"ref34","first-page":"797","article-title":"Escaping from saddle points - online stochastic gradient for tensor decomposition","volume-title":"Proc. 28th Conf. Learn. Theory","author":"Ge","year":"2015"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4613-3557-3","volume-title":"Minimax and Applications","volume":"4","author":"Du","year":"1995"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref37","article-title":"Towards deep learning models resistant to adversarial attacks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Madry","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-4286-2"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1080\/00207721.2014.925608"},{"issue":"61","key":"ref40","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":"ref41","article-title":"Pytorch implementation of adagrad","year":"2023"},{"key":"ref42","article-title":"Pytorch implementation of RMSprop","year":"2023"},{"issue":"73","key":"ref43","first-page":"1","article-title":"Optimization with momentum: Dynamical, control-theoretic, and symplectic perspectives","volume":"22","author":"Muehlebach","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3214795"},{"key":"ref45","first-page":"20640","article-title":"Continuous-time analysis of accelerated gradient methods via conservation laws in dilated coordinate systems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Suh","year":"2022"},{"key":"ref46","article-title":"When are nonconvex problems not scary","author":"Sun","year":"2015"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref48","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref49","article-title":"Neural networks for machine learning, lecture 6a, overview of mini-batch gradient descent","author":"Hinton","year":"2012"},{"key":"ref50","first-page":"314","article-title":"Stochastic variance reduction for nonconvex optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reddi","year":"2016"},{"key":"ref51","article-title":"Adam is no better than normalized SGD: Dissecting how adaptivity improves GAN performance","author":"Jelassi","year":"2022"},{"key":"ref52","volume-title":"Geometric Measure Theory","author":"Federer","year":"2014"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10485216\/10301676.pdf?arnumber=10301676","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T15:10:34Z","timestamp":1711984234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10301676\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":52,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tac.2023.3328510","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}