{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T22:20:29Z","timestamp":1780698029114,"version":"3.54.1"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,9]]},"DOI":"10.1109\/allerton.2014.7028543","type":"proceedings-article","created":{"date-parts":[[2015,2,5]],"date-time":"2015-02-05T19:24:07Z","timestamp":1423164247000},"page":"850-857","source":"Crossref","is-referenced-by-count":52,"title":["Distributed stochastic optimization and learning"],"prefix":"10.1109","author":[{"given":"Ohad","family":"Shamir","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nathan","family":"Srebro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"19","article-title":"Stochastic convex optimization","author":"shalev-shwartz","year":"2009","journal-title":"COLT"},{"key":"17","article-title":"Making gradient descent optimal for strongly convex stochastic optimization","author":"rakhlin","year":"2012","journal-title":"ICML"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-010-9737-7"},{"key":"15","author":"nemirovski","year":"1978","journal-title":"Problem Complexity and Method Efficiency in Optimization"},{"key":"16","first-page":"372","article-title":"A method of solving a convex programming problem with convergence rate o(1=k2)","volume":"27","author":"nesterov","year":"1983","journal-title":"Soviet Mathematics Doklady"},{"key":"13","author":"iutzeler","year":"2013","journal-title":"Explicit Convergence Rate of A Distributed Alternating Direction Method of Multipliers"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"11","article-title":"Beating SGD: Learning svms in sublinear time","author":"hazan","year":"2011","journal-title":"NIPS"},{"key":"12","author":"hong","year":"2012","journal-title":"On the linear convergence of the alternating direction method of multipliers"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390273"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-010-0420-4"},{"key":"22","article-title":"Communication efficient distributed optimization using an approximate newton-type method","author":"shamir","year":"2014","journal-title":"ICML"},{"key":"23","article-title":"Stochastic gradient descent for non-smooth optimization: Convergence results and optimal averaging schemes","author":"shamir","year":"2013","journal-title":"ICML"},{"key":"24","article-title":"Smoothness, low noise and fast rates","author":"srebro","year":"2010","journal-title":"NIPS"},{"key":"25","article-title":"On the universality of online mirror descent","author":"srebro","year":"2011","journal-title":"NIPS"},{"key":"26","author":"sridharan","year":"2012","journal-title":"Learning from An Optimization Viewpoint"},{"key":"27","article-title":"Mini-batch primal and dual methods for svms","author":"tak\ufffdc","year":"2013","journal-title":"ICML"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2440-0"},{"key":"29","first-page":"3321","article-title":"Communication-efficient algorithms for statistical optimization","volume":"14","author":"zhang","year":"2013","journal-title":"J of Machine Learning Research"},{"key":"3","article-title":"Non-asymptotic analysis of stochastic approximation algorithms for machine learning","author":"bach","year":"2011","journal-title":"NIPS"},{"key":"2","article-title":"Distributed delayed stochastic optimization","author":"agarwal","year":"2011","journal-title":"NIPS"},{"key":"10","article-title":"Beyond the regret minimization barrier: An optimal algorithm for stochastic strongly-convex optimization","author":"hazan","year":"2011","journal-title":"COLT"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-010-0434-y"},{"key":"30","article-title":"Parallelized stochastic gradient descent","author":"zinkevich","year":"2010","journal-title":"NIPS"},{"key":"7","article-title":"Better mini-batch algorithms via accelerated gradient methods","author":"cotter","year":"2011","journal-title":"NIPS"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"5","article-title":"The tradeoffs of large scale learning","author":"bottou","year":"2007","journal-title":"NIPS"},{"key":"4","article-title":"Distributed learning, communication complexity and privacy","author":"balcan","year":"2012","journal-title":"COLT"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5016-8"},{"key":"8","first-page":"165","article-title":"Optimal distributed online prediction using mini-batches","volume":"13","author":"dekel","year":"2012","journal-title":"J of Machine Learning Research"}],"event":{"name":"2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton)","location":"Monticello, IL, USA","start":{"date-parts":[[2014,9,30]]},"end":{"date-parts":[[2014,10,3]]}},"container-title":["2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7008053\/7028426\/07028543.pdf?arnumber=7028543","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,24]],"date-time":"2017-03-24T05:31:41Z","timestamp":1490333501000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7028543\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,9]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/allerton.2014.7028543","relation":{},"subject":[],"published":{"date-parts":[[2014,9]]}}}