{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T12:22:19Z","timestamp":1725625339499},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"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":[[2021,12,15]]},"DOI":"10.1109\/bigdata52589.2021.9671966","type":"proceedings-article","created":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T20:39:16Z","timestamp":1642106356000},"page":"1002-1007","source":"Crossref","is-referenced-by-count":0,"title":["How Shrinking Gradient Noise Helps the Performance of Neural Networks"],"prefix":"10.1109","author":[{"given":"Zhun","family":"Deng","sequence":"first","affiliation":[{"name":"Harvard University,John A. Paulson School of Engineering and Applied Science,Cambridge,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaoyang","family":"Huang","sequence":"additional","affiliation":[{"name":"New York University,Courant Institute of Mathematical Sciences,New York,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenji","family":"Kawaguchi","sequence":"additional","affiliation":[{"name":"Harvard University,Center of Mathematical Sciences and Applications,Cambridge,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","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"},{"key":"ref11","first-page":"1724","article-title":"How to escape saddle points efficiently","author":"jin","year":"0"},{"key":"ref12","first-page":"586","article-title":"Deep learning without poor local minima","author":"kawaguchi","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10200","article-title":"Preconditioned stochastic gradient langevin dynamics for deep neural networks","author":"li","year":"2016","journal-title":"THIRTIETH AAAI Conference on Artificial Intelligence"},{"journal-title":"Ensemble noise simulation to handle uncertainty about gradient-based adversarial attacks","year":"2020","author":"mahfuz","key":"ref14"},{"journal-title":"Adding gradient noise improves learning for very deep networks","year":"2015","author":"neelakantan","key":"ref15"},{"journal-title":"Non-convex learning via Stochastic Gradient Langevin Dynamics a nonasymptotic analysis","year":"2017","author":"raginsky","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21852-6_3"},{"key":"ref18","first-page":"2493","article-title":"Privacy for free: Posterior sampling and stochastic gradient monte carlo","author":"wang","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref19","first-page":"681","article-title":"Bayesian learning via stochastic gradient langevin dynamics","author":"welling","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"journal-title":"Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks","year":"2019","author":"arora","key":"ref4"},{"journal-title":"On exact computation with an infinitely wide neural net","year":"2019","author":"arora","key":"ref3"},{"key":"ref6","first-page":"1067","article-title":"Gradient descent can take exponential time to escape saddle points","author":"du","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"12873","article-title":"On the inductive bias of neural tangent kernels","author":"bietti","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"797","article-title":"Escaping from saddle points&#x2014;online stochastic gradient for tensor decomposition","author":"ge","year":"2015","journal-title":"Proceedings of The 28th Conference on Learning Theory"},{"journal-title":"Gradient descent provably optimizes over-parameterized neural networks","year":"2018","author":"du","key":"ref7"},{"key":"ref2","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":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref9","first-page":"2973","article-title":"Matrix completion has no spurious local minimum","author":"ge","year":"2016","journal-title":"Advances in neural information processing systems"},{"journal-title":"Global optimality conditions for deep neural networks","year":"2017","author":"yun","key":"ref20"},{"journal-title":"Learning one-hidden-layer relu networks via gradient descent","year":"2018","author":"zhang","key":"ref21"}],"event":{"name":"2021 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2021,12,15]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2021,12,18]]}},"container-title":["2021 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9671263\/9671273\/09671966.pdf?arnumber=9671966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T22:06:19Z","timestamp":1674425179000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9671966\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/bigdata52589.2021.9671966","relation":{},"subject":[],"published":{"date-parts":[[2021,12,15]]}}}