{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T11:13:27Z","timestamp":1730200407766,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,10]],"date-time":"2020-12-10T00:00:00Z","timestamp":1607558400000},"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":[[2020,12,10]]},"DOI":"10.1109\/bigdata50022.2020.9378212","type":"proceedings-article","created":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T21:10:21Z","timestamp":1616188221000},"page":"112-122","source":"Crossref","is-referenced-by-count":0,"title":["Improving Model Training by Periodic Sampling over Weight Distributions"],"prefix":"10.1109","author":[{"given":"Samarth","family":"Tripathi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sauptik","family":"Dhar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Unmesh","family":"Kurup","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohak","family":"Shah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2012","author":"lacoste-julien","article-title":"A simpler approach to obtaining an O(1\/t) convergence rate for the projected stochastic subgradient method","key":"ref10"},{"key":"ref11","first-page":"451","article-title":"Non-Asymptotic Analysis of Stochastic Approximation Algorithms for Machine Learning","author":"moulines","year":"2011","journal-title":"Advances in Neural Information Processing Systems 24"},{"year":"2017","author":"smith","journal-title":"Don’t decay the learning rate increase the batch size","key":"ref12"},{"key":"ref13","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"},{"year":"2018","author":"liu","journal-title":"Make (nearly) every neural network better Generating neural network ensembles by weight parameter resampling","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/CVPR.2018.00474"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/CVPR.2017.243"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/CVPR.2016.308"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref19","volume":"7","author":"peng","year":"2017","journal-title":"Megdet A large mini-batch object detector"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1017\/CBO9781107298019.015"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref27","first-page":"71","article-title":"Stochastic gradient descent for non-smooth optimization: Convergence results and optimal averaging schemes","author":"shamir","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref3","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"The Journal of Machine Learning Research"},{"year":"2018","author":"izmailov","journal-title":"Averaging weights leads to wider optima and better generalization","key":"ref6"},{"year":"2015","author":"ioffe","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","key":"ref5"},{"key":"ref8","article-title":"Adam: a Method for Stochastic Optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations"},{"year":"2017","author":"keskar","journal-title":"Improving generalization performance by switching from adam to sgd","key":"ref7"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref9","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009","journal-title":"Technical Report Citeseer"},{"key":"ref1","article-title":"DAWNBench: An End-to-End Deep Learning Benchmark and Competition","author":"coleman","year":"2017","journal-title":"NIPS ML Systems Workshop"},{"year":"2016","author":"zhou","journal-title":"Semantic Understanding of Scenes through ADE20K Dataset","key":"ref20"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CVPR.2017.243"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1162\/neco.1997.9.1.1"},{"key":"ref24","first-page":"586","article-title":"Deep learning without poor local minima","author":"kawaguchi","year":"2016","journal-title":"Advances in neural information processing systems"},{"year":"2018","author":"izmailov","journal-title":"Averaging weights leads to wider optima and better generalization","key":"ref23"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1007\/978-3-030-01228-1_26"},{"year":"2017","author":"li","journal-title":"Visualizing the Loss Landscape of Neural Nets","key":"ref25"}],"event":{"name":"2020 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2020,12,10]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2020,12,13]]}},"container-title":["2020 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9377717\/9377728\/09378212.pdf?arnumber=9378212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T16:12:47Z","timestamp":1656346367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9378212\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,10]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/bigdata50022.2020.9378212","relation":{},"subject":[],"published":{"date-parts":[[2020,12,10]]}}}