{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T01:12:57Z","timestamp":1725585177836},"reference-count":19,"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\/icassp40776.2020.9053999","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"3992-3996","source":"Crossref","is-referenced-by-count":1,"title":["Anytime Minibatch with Delayed Gradients: System Performance and Convergence Analysis"],"prefix":"10.1109","author":[{"given":"Haider","family":"Al-Lawati","sequence":"first","affiliation":[]},{"given":"Stark C.","family":"Draper","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"2331","article-title":"Slow learners are fast","author":"zinkevich","year":"2009","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref11","first-page":"2737","article-title":"Asynchronous parallel stochastic gradient for nonconvex optimization","author":"lian","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2017.0-166"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2018.8635903"},{"key":"ref14","article-title":"Anytime minibatch: Exploiting stragglers in online distributed optimization","author":"ferdinand","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref15","first-page":"1","article-title":"Anytime minibatch with stale gradients","author":"al-lawati","year":"2019","journal-title":"Proc of Conf on Info Sciences and Sys"},{"key":"ref16","first-page":"803","article-title":"Slow and stale gradients can win the race: Error-runtime trade-offs in distributed SGD","author":"dutta","year":"2018","journal-title":"Proc Int Conf on Artificial Intelligence"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-007-0149-x"},{"key":"ref18","first-page":"2116","article-title":"Dual averaging method for regularized stochastic learning and online optimization","author":"xiao","year":"2009","journal-title":"Adv Neural Inf Process Syst"},{"article-title":"MNIST handwritten digit database","year":"2010","author":"lecun","key":"ref19"},{"key":"ref4","first-page":"2595","article-title":"Parallelized stochastic gradient descent","author":"zinkevich","year":"2010","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref3","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref6","first-page":"217","article-title":"Large scale online learning","author":"bottou","year":"2004","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"165","article-title":"Optimal distributed online prediction using minibatches","author":"dekel","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2161027"},{"key":"ref7","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref2","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref1","article-title":"Revisiting distributed synchronous sgd","author":"chen","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref9","article-title":"Accelerating Stochastic Gradient Descent For Least Squares Regression","author":"jain","year":"2017","journal-title":"ArXiv e-prints"}],"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\/09053999.pdf?arnumber=9053999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:07:17Z","timestamp":1656374837000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053999\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053999","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}