Show simple item record

dc.contributor.authorWoodworth, Blakeen_US
dc.contributor.authorWang, Jialeien_US
dc.contributor.authorSmith, Adamen_US
dc.contributor.authorMcMahan, Brendanen_US
dc.contributor.authorSrebro, Natien_US
dc.date.accessioned2019-09-18T13:34:53Z
dc.date.available2019-09-18T13:34:53Z
dc.date.issued2018-12-01
dc.identifier.citationBlake Woodworth, Jialei Wang, Adam Smith, Brendan McMahan, Nati Srebro. 2018. "Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization." Advances in Neural Information Processing Systems 31 (NIPS 2018), pp. 8505-8515.
dc.identifier.urihttps://hdl.handle.net/2144/37837
dc.description.abstractWe suggest a general oracle-based framework that captures different parallel stochastic optimization settings described by a dependency graph, and derive generic lower bounds in terms of this graph. We then use the framework and derive lower bounds for several specific parallel optimization settings, including delayed updates and parallel processing with intermittent communication. We highlight gaps between lower and upper bounds on the oracle complexity, and cases where the "natural" algorithms are not known to be optimal.en_US
dc.description.urihttp://papers.nips.cc/paper/8069-graph-oracle-models-lower-bounds-and-gaps-for-parallel-stochastic-optimization
dc.titleGraph oracle models, lower bounds, and gaps for parallel stochastic optimizationen_US
dc.typeConference materialsen_US
dc.description.versionPublished versionen_US
pubs.elements-sourcemanual-entryen_US
pubs.notesEmbargo: Not knownen_US
pubs.organisational-groupBoston Universityen_US
pubs.organisational-groupBoston University, College of Arts & Sciencesen_US
pubs.organisational-groupBoston University, College of Arts & Sciences, Department of Computer Scienceen_US
pubs.publication-statusPublisheden_US
dc.identifier.mycv467002


This item appears in the following Collection(s)

Show simple item record