{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:08:11Z","timestamp":1759104491587},"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\/icassp40776.2020.9054587","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"4207-4211","source":"Crossref","is-referenced-by-count":9,"title":["Gradient Delay Analysis in Asynchronous Distributed Optimization"],"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":"1","article-title":"Anytime minibatch with stale gradients","author":"al-lawati","year":"2019","journal-title":"Proc of Conf on Info Sciences and Sys"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2525015"},{"key":"ref12","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","author":"feng","year":"2011","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref13","first-page":"2737","article-title":"Asynchronous parallel stochastic gradient for nonconvex optimization","author":"lian","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/S1570-579X(01)80023-9"},{"key":"ref15","first-page":"873","article-title":"Distributed delayed stochastic optimization","author":"agarwal","year":"2011","journal-title":"Adv Neural Inf Process Syst"},{"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":"10.1109\/TIT.2017.2736066"},{"key":"ref18","article-title":"Speeding up distributed gradient descent by utilizing non-persistent stragglers","author":"ozfatura","year":"2018","journal-title":"CoRR"},{"key":"ref19","first-page":"2092","article-title":"Short-dot: Computing large linear transforms distributedly using coded short dot products","author":"dutta","year":"2016","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref4","article-title":"Revisiting distributed synchronous sgd","author":"chen","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref3","first-page":"489","article-title":"Efficient distributed online prediction and stochastic optimization with approximate distributed averaging","author":"konstantinos","year":"2016","journal-title":"IEEE Trans Sig Inf Process Net"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CAMSAP.2017.8313171"},{"key":"ref5","first-page":"1223","article-title":"More effective distributed ml via a stale synchronous parallel parameter server","author":"ho","year":"2013","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2016.2611578"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2408776.2408794"},{"key":"ref2","first-page":"2331","article-title":"Slow learners are fast","author":"zinkevich","year":"2009","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref1","first-page":"165","article-title":"Optimal distributed online prediction using mini-batches","author":"dekel","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","article-title":"Improving mapreduce performance in heterogeneous environments","author":"zaharia","year":"2008","journal-title":"Proc of USENIX Conf on Operating Sys Design and Imp"}],"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\/09054587.pdf?arnumber=9054587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:21:35Z","timestamp":1656375695000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054587\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054587","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}