{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:34:03Z","timestamp":1730230443262,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053864","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"3132-3136","source":"Crossref","is-referenced-by-count":6,"title":["A Study of Generalization of Stochastic Mirror Descent Algorithms on Overparameterized Nonlinear Models"],"prefix":"10.1109","author":[{"given":"Navid","family":"Azizan","sequence":"first","affiliation":[]},{"given":"Sahin","family":"Lale","sequence":"additional","affiliation":[]},{"given":"Babak","family":"Hassibi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"3325","article-title":"The power of interpolation: Understanding the effectiveness of SGD in modern over-parametrized learning","volume":"80","author":"ma","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"article-title":"Geometry of optimization and implicit regularization in deep learning","year":"2017","author":"neyshabur","key":"ref11"},{"key":"ref12","first-page":"1827","article-title":"Characterizing implicit bias in terms of optimization geometry","author":"gunasekar","year":"2018","journal-title":"International Conference on Machine Learning"},{"article-title":"The implicit bias of gradient descent on separable data","year":"2017","author":"soudry","key":"ref13"},{"key":"ref14","article-title":"Stochastic gradient\/mirror descent: Minimax optimality and implicit regularization","author":"azizan","year":"2019","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682271"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"journal-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref17"},{"article-title":"Stochastic mirror descent on overparameterized nonlinear models: Convergence, implicit regularization, and generalization","year":"2019","author":"azizan","key":"ref18"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6377(02)00231-6"},{"key":"ref3","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref6","first-page":"980","article-title":"Mirror descent meets fixed share (and feels no regret)","author":"cesa-bianchi","year":"2012","journal-title":"Advances in neural information processing systems"},{"article-title":"Problem complexity and method efficiency in optimization","year":"1983","author":"nemirovski","key":"ref5"},{"key":"ref8","article-title":"Overparameterized nonlinear learning: Gradient descent takes the shortest pathƒ","author":"oymak","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref7","first-page":"7043","article-title":"Stochastic mirror descent in variationally coherent optimization problems","author":"zhou","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Understanding deep learning requires rethinking generalization","year":"2016","author":"zhang","key":"ref2"},{"key":"ref1","first-page":"254","article-title":"Stronger generalization bounds for deep nets via a compression approach","author":"arora","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref9","article-title":"A convergence theory for deep learning via over-parameterization","author":"allen-zhu","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053864.pdf?arnumber=9053864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:14:45Z","timestamp":1656375285000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053864\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053864","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}