{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T09:10:11Z","timestamp":1771060211277,"version":"3.50.1"},"reference-count":84,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/cdc40024.2019.9029197","type":"proceedings-article","created":{"date-parts":[[2020,3,13]],"date-time":"2020-03-13T04:43:11Z","timestamp":1584074591000},"page":"4563-4568","source":"Crossref","is-referenced-by-count":30,"title":["Connections Between Adaptive Control and Optimization in Machine Learning"],"prefix":"10.1109","author":[{"given":"Joseph E.","family":"Gaudio","sequence":"first","affiliation":[]},{"given":"Travis E.","family":"Gibson","sequence":"additional","affiliation":[]},{"given":"Anuradha M.","family":"Annaswamy","sequence":"additional","affiliation":[]},{"given":"Michael A.","family":"Bolender","sequence":"additional","affiliation":[]},{"given":"Eugene","family":"Lavretsky","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"crossref","DOI":"10.1561\/9781601981851","volume":"1","author":"wainwright","year":"2007","journal-title":"Graphical models exponential families and variational inference"},{"key":"ref72","first-page":"1385","article-title":"Sharing clusters among related groups: Hierarchical dirichlet processes","author":"teh","year":"2005","journal-title":"Advances in Neural Information Processing Systems 17"},{"key":"ref71","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.809146"},{"key":"ref76","first-page":"372","article-title":"A method of solving a convex programming problem with convergence rate $O\\left( {1\/{k^2}} \\right)$","volume":"27","author":"nesterov","year":"1983","journal-title":"Soviet Mathematics Doklady"},{"key":"ref77","first-page":"1","article-title":"A differential equation for modeling nesterov’s accelerated gradient method: Theory and insights","volume":"17","author":"su","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1017\/9781108627771"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1986.1104259"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1137\/080716542"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(82)90021-8"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1614734113"},{"key":"ref79","article-title":"A lyapunov analysis of momentum methods in optimization","author":"wilson","year":"2016"},{"key":"ref33","first-page":"1225","article-title":"Train faster, generalize better: Stability of stochastic gradient descent","volume":"48","author":"hardt","year":"2016","journal-title":"Proceedings of the 33rd International Conference on Machine Learning"},{"key":"ref32","first-page":"499","article-title":"Stability and generalization","volume":"2","author":"bousquet","year":"2002","journal-title":"Journal of Machine Learning Research"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(95)00059-6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/9.333787"},{"key":"ref37","author":"goodwin","year":"1984","journal-title":"Adaptive Filtering Prediction and Control"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(86)90002-6"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(83)90071-3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/15M1047805"},{"key":"ref60","first-page":"448","article-title":"Optimal perceptual inference","author":"hinton","year":"1983","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref62","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2017"},{"key":"ref64","author":"hebb","year":"1949","journal-title":"The Organization of Behavior"},{"key":"ref27","article-title":"Adadelta: an adaptive learning rate method","author":"zeiler","year":"2012"},{"key":"ref65","first-page":"244","article-title":"On the optimization of deep networks: Implicit acceleration by overparameterization","volume":"80","author":"arora","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref66","article-title":"A convergence analysis of gradient descent for deep linear neural networks","author":"arora","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref29","article-title":"On the convergence of adam and beyond","author":"reddi","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.1991.4791778"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/9.788531"},{"key":"ref2","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref1","author":"duda","year":"2001","journal-title":"Pattern Classification"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/00207179508921605"},{"key":"ref22","article-title":"Robust adaptive control in the presence of unmodeled dynamics","author":"hussain","year":"2017","journal-title":"Ph D Dissertation"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1982.1103093"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5016-8"},{"key":"ref23","article-title":"Projection operator in adaptive systems","author":"lavretsky","year":"2012"},{"key":"ref26","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref25","first-page":"928","article-title":"Online convex programming and generalized infinitesimal gradient ascent","author":"zinkevich","year":"2003","journal-title":"Proceedings of the 20th International Conference on Machine Learning (ICML-03)"},{"key":"ref50","article-title":"A gradient method for optimizing multistage allocation processes","author":"bryson","year":"1961","journal-title":"Proc Harvard Symp on Digital Computers and Their Applications"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.2514\/3.25422"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.79.8.2554"},{"key":"ref58","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","volume":"28","author":"sutskever","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning"},{"key":"ref57","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems 25"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(98)00012-0"},{"key":"ref55","first-page":"1010","article-title":"Neural control for nonlinear dynamic systems","author":"yu","year":"1996","journal-title":"Advances in Neural Information Processing Systems 8"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/72.80336"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/72.80202"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-57760-4"},{"key":"ref10","author":"ioannou","year":"1996","journal-title":"Robust Adaptive Control"},{"key":"ref11","author":"narendra","year":"2005","journal-title":"Stable Adaptive Systems"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1080\/00207178708933715"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029197"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1984.1103490"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1987.1104543"},{"key":"ref15","first-page":"65","article-title":"Adaptive online gradient descent","author":"hazan","year":"2008","journal-title":"Advances in Neural Information Processing Systems 20"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2204-8_23"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1561\/2200000050"},{"key":"ref81","article-title":"On symplectic optimization","author":"betancourt","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1561\/2400000013"},{"key":"ref84","article-title":"Provably correct learning algorithms in the presence of time-varying features using a variational perspective","author":"gaudio","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1982.1103112"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1115\/1.1567755"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00010-0"},{"key":"ref80","article-title":"Lyapunov arguments in optimization","author":"wilson","year":"2018","journal-title":"Ph D Dissertation"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781316576533"},{"key":"ref3","author":"hastie","year":"2009","journal-title":"The Elements of Statistical Learning Data Mining Inference and Prediction"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa8415"},{"key":"ref5","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref8","author":"sastry","year":"1989","journal-title":"Adaptive Control Stability Convergence and Robustness"},{"key":"ref7","author":"narendra","year":"1989","journal-title":"Stable Adaptive Systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.2514\/8.5282"},{"key":"ref9","author":"\u00e5str\u00f6m","year":"1995","journal-title":"Adaptive Control Second Edition"},{"key":"ref46","first-page":"2973","article-title":"Matrix completion has no spurious local minimum","author":"ge","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref45","first-page":"192","article-title":"The loss surfaces of multilayer networks","volume":"38","author":"choromanska","year":"2015","journal-title":"Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref48","author":"pontryagin","year":"1961","journal-title":"Mathematical Theory of Optimal Processes"},{"key":"ref47","first-page":"1246","article-title":"Gradient descent only converges to minimizers","volume":"49","author":"lee","year":"2016","journal-title":"29th Annual Conference on Learning Theory"},{"key":"ref42","first-page":"4192","article-title":"Regret bounds for robust adaptive control of the linear quadratic regulator","author":"dean","year":"2018","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref41","author":"ljung","year":"1987","journal-title":"System Identification Theory for the User"},{"key":"ref44","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/37.126844","article-title":"Reinforcement learning is direct adaptive optimal control","volume":"12","author":"sutton","year":"1992","journal-title":"IEEE Control Systems"}],"event":{"name":"2019 IEEE 58th Conference on Decision and Control (CDC)","location":"Nice, France","start":{"date-parts":[[2019,12,11]]},"end":{"date-parts":[[2019,12,13]]}},"container-title":["2019 IEEE 58th Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8977134\/9028853\/09029197.pdf?arnumber=9029197","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T20:24:32Z","timestamp":1658262272000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9029197\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/cdc40024.2019.9029197","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}