{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T12:40:59Z","timestamp":1725712859202},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"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":[[2020,12,14]]},"DOI":"10.1109\/cdc42340.2020.9304386","type":"proceedings-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T07:27:32Z","timestamp":1610522852000},"page":"4683-4688","source":"Crossref","is-referenced-by-count":4,"title":["The Role of Regularization in Overparameterized Neural Networks"],"prefix":"10.1109","author":[{"given":"Siddhartha","family":"Satpathi","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana Champaign,Department of Electrical and Computer Engineering and the Coordinated Science Lab,Champaign,IL,USA,61820"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harsh","family":"Gupta","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana Champaign,Department of Electrical and Computer Engineering and the Coordinated Science Lab,Champaign,IL,USA,61820"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyu","family":"Liang","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana Champaign,Department of Electrical and Computer Engineering and the Coordinated Science Lab,Champaign,IL,USA,61820"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R","family":"Srikant","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana Champaign,Department of Electrical and Computer Engineering and the Coordinated Science Lab,Champaign,IL,USA,61820"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow relu networks","year":"2019","author":"ji","key":"ref10"},{"article-title":"How much over-parameterization is sufficient to learn deep relu networks?","year":"2019","author":"chen","key":"ref11"},{"article-title":"Generalization error bounds of gradient descent for learning overparameterized deep relu networks","year":"2019","author":"cao","key":"ref12"},{"key":"ref13","first-page":"2053","article-title":"An improved analysis of training overparameterized deep neural networks","author":"zou","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","author":"allen-zhu","year":"2019","journal-title":"International Conference on Machine Learning"},{"article-title":"Stochastic gradient descent optimizes over-parameterized deep relu networks","year":"2018","author":"zou","key":"ref15"},{"key":"ref16","first-page":"6155","article-title":"Learning and generalization in overparameterized neural networks, going beyond two layers","author":"allen-zhu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref19","first-page":"950","article-title":"A simple weight decay can improve generalization","author":"krogh","year":"1992","journal-title":"Advances in neural information processing systems"},{"key":"ref4","first-page":"2835","article-title":"Understanding the loss surface of neural networks for binary classification","author":"liang","year":"2018","journal-title":"International Conference on Machine Learning"},{"article-title":"The loss landscape of overparameterized neural networks","year":"2018","author":"cooper","key":"ref3"},{"article-title":"Fine-grained analysis of optimization and generalization for over-parameterized two-layer neural networks","year":"2019","author":"arora","key":"ref6"},{"article-title":"Revisiting landscape analysis in deep neural networks: Eliminating decreasing paths to infinity","year":"2019","author":"liang","key":"ref5"},{"key":"ref8","article-title":"Simple and effective regularization methods for training on noisily labeled data with generalization guarantee","author":"hu","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref7","first-page":"8080","article-title":"Fast convergence of natural gradient descent for over-parameterized neural networks","author":"zhang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref2","first-page":"6389","article-title":"Visualizing the loss landscape of neural nets","author":"li","year":"2018","journal-title":"Advances in Neural IInformation Processing Systems"},{"article-title":"On the benefit of width for neural networks: Disappearance of bad basins","year":"2018","author":"li","key":"ref1"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1109\/CDC42340.2020.9304386","article-title":"The role of regularization in overparameterized neural networks","author":"satpathi","year":"2020"},{"key":"ref20","first-page":"2933","article-title":"On lazy training in differentiable programming","author":"chizat","year":"2019","journal-title":"Advances in neural information processing systems"},{"article-title":"Gradient descent provably optimizes over-parameterized neural networks","year":"0","author":"du","key":"ref22"},{"key":"ref21","first-page":"8571","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","author":"jacot","year":"2018","journal-title":"Advances in neural information processing systems"},{"journal-title":"Foundations of Machine Learning","year":"2018","author":"mohri","key":"ref23"}],"event":{"name":"2020 59th IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2020,12,14]]},"location":"Jeju, Korea (South)","end":{"date-parts":[[2020,12,18]]}},"container-title":["2020 59th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9303728\/9303729\/09304386.pdf?arnumber=9304386","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T19:12:11Z","timestamp":1674241931000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9304386\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cdc42340.2020.9304386","relation":{},"subject":[],"published":{"date-parts":[[2020,12,14]]}}}