{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:29:41Z","timestamp":1756312181713,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T00:00:00Z","timestamp":1607904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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\/cdc42340.2020.9303830","type":"proceedings-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T07:27:32Z","timestamp":1610522852000},"page":"3580-3585","source":"Crossref","is-referenced-by-count":5,"title":["Taming Convergence for Asynchronous Stochastic Gradient Descent with Unbounded Delay in Non-Convex Learning"],"prefix":"10.1109","author":[{"given":"Xin","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Jia","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zhengyuan","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","author":"recht","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"2737","article-title":"Asynchronous parallel stochastic gradient for nonconvex optimization","author":"lian","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref12","first-page":"4120","article-title":"Asynchronous stochastic gradient descent with delay compensation","author":"zheng","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref13","first-page":"2043","article-title":"Asynchronous mini-batch gradient descent with variance reduction for non-convex optimization","author":"huo","year":"2017","journal-title":"AAAI"},{"key":"ref14","first-page":"873","article-title":"Distributed delayed stochastic optimization","author":"agarwal","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-017-0628-z"},{"article-title":"Taming convergence for asynchronous stochastic gradient descent with unbounded delay in non-convex learning","year":"2018","author":"zhang","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/140971233"},{"key":"ref18","first-page":"2332","article-title":"Global convergence of stochastic gradient descent for some non-convex matrix problems","author":"de sa","year":"2015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2010.5706976"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-013-0682-2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2012.168"},{"key":"ref6","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Advances in neural information processing systems"},{"article-title":"Parallel matrix factorization for low-rank tensor completion","year":"2013","author":"xu","key":"ref5"},{"key":"ref8","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"OSDI"},{"article-title":"Parallel training of dnns with natural gradient and parameter averaging","year":"2014","author":"povey","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC.2005.1527207"},{"journal-title":"Gordon Moore Predicts 10 More Years for Moore’s Law","year":"2015","author":"poeter","key":"ref1"},{"key":"ref9","first-page":"3","article-title":"Scaling distributed machine learning with the parameter server","volume":"1","author":"li","year":"2014","journal-title":"OSDI"},{"article-title":"Old and new matrix algebra useful for statistics","year":"2000","author":"minka","key":"ref20"}],"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\/09303830.pdf?arnumber=9303830","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:46:41Z","timestamp":1656344801000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9303830\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/cdc42340.2020.9303830","relation":{},"subject":[],"published":{"date-parts":[[2020,12,14]]}}}