Variable metric stochastic approximation theory

Simple item page
dc.contributor.authorSunehag, Peteren
dc.contributor.authorTrumpf, Jochenen
dc.contributor.authorVishwanathan, S. V.N.en
dc.contributor.authorSchraudolph, Nicol N.en
dc.date.accessioned2025-12-31T21:42:00Z
dc.date.available2025-12-31T21:42:00Z
dc.date.issued2009en
dc.description.abstractWe provide a variable metric stochastic approximation theory. In doing so, we provide a convergence theory for a large class of online variable metric methods including the recently introduced online versions of the BFGS algorithm and its limited-memory LBFGS variant. We also discuss the implications of our results for learning from expert advice.en
dc.description.statusPeer-revieweden
dc.format.extent7en
dc.identifier.issn1532-4435en
dc.identifier.scopus84862282880en
dc.identifier.urihttps://hdl.handle.net/1885/733798295
dc.language.isoenen
dc.relation.ispartofseries12th International Conference on Artificial Intelligence and Statistics, AISTATS 2009en
dc.sourceJournal of Machine Learning Researchen
dc.titleVariable metric stochastic approximation theoryen
dc.typeConference paperen
dspace.entity.typePublicationen
local.bibliographicCitation.lastpage566en
local.bibliographicCitation.startpage560en
local.contributor.affiliationSunehag, Peter; School of Computing, ANU College of Systems and Society, The Australian National Universityen
local.contributor.affiliationTrumpf, Jochen; School of Engineering, ANU College of Systems and Society, The Australian National Universityen
local.contributor.affiliationVishwanathan, S. V.N.; Purdue Universityen
local.contributor.affiliationSchraudolph, Nicol N.; Adaptive Tools AGen
local.identifier.ariespublicationu4334215xPUB223en
local.identifier.citationvolume5en
local.identifier.pure722ff2e5-4b28-45d4-81d1-ec5c3825ec26en
local.identifier.urlhttps://www.scopus.com/pages/publications/84862282880en
local.type.statusPublisheden

Downloads

Collections

ANU Research Publications

DSpace software copyright © 2002-2026 LYRASIS