FairnessofExposureinStochasticBanditsLequnWang1YiweiBai1WenSun1ThorstenJoachims1AbstractWhilemaximizinguserresponsesmayarguablybeintheinterestoftheplatformanditsusersatleastintheshortterm,Contextua...
EquivariantLearningofStochasticFields:GaussianProcessesandSteerableConditionalNeuralProcessesPeterHolderrieth1MichaelHutchinson1YeeWhyeTeh12AbstractFigure1.Aschematicofequivariantlearningofvectorfi...
DecentralizedSingle-TimescaleActorCriticonZero-SumTwo-PlayerStochasticGamesHongyiGuo1ZuyueFu1ZhuoranYang2ZhaoranWang1AbstractasMarkovdecisionprocess(Puterman,2014,MDP),whereanagentaimstolearnanopti...
CombinatorialBlockingBanditswithStochasticDelaysAlexiaAtsidakou1OrestisPapadigenopoulos2SoumyaBasu3ConstantineCaramanis1SanjayShakkottai1AbstractCella&Cesa-Bianchi,2019).Thesevariantscaptureappli-c...
BetterTrainingusingWeight-ConstrainedStochasticDynamicsBenedictLeimkuhler1TiffanyVlaar1Timothe´ePouchon1AmosStorkey2AbstractCurrentapproachestoenhancethegeneralizationperfor-manceofoverparameteriz...
AnalysisofStochasticLanczosquadratureforspectrumapproximationTylerChen1ThomasTrogdon1ShashankaUbaru2Abstractdependingonjustthespectrum.Conversely,computingtheCESMrequiresexactknowledgeofalltheeigen...
AnAlgorithmforStochasticandAdversarialBanditswithSwitchingCostsChloe´Rouyer1YevgenySeldin1Nicolo`Cesa-Bianchi2Abstractanarmdifferentfromtheoneplayedinthepreviousround.Suchswitchingcostmayoccurinth...
AchievingNearInstance-OptimalityandMinimax-OptimalityinStochasticandAdversarialLinearBanditsSimultaneouslyChung-WeiLee1HaipengLuo1Chen-YuWei1MengxiaoZhang1XiaojinZhang2Abstractadversarialenvironmen...
AsynchronousDecentralizedOptimizationWithImplicitStochasticVarianceReductionKentaNiwa12GuoqiangZhang3W.BastiaanKleijn4NoboruHarada12HiroshiSawada1AkinoriFujino1AbstractOurgoalistofacilitateMLmodelt...
AHybridVariance-ReducedMethodforDecentralizedStochasticNon-ConvexOptimizationRanXin1UsmanA.Khan2SoummyaKar1Abstractistosolve,vialocalcomputationandcommunication,thefollowingoptimizationproblem:This...
VarianceReductioninStochasticParticle-OptimizationSamplingJianyiZhang1YangZhao2RuiyiZhang1LawrenceCarin1ChangyouChen2AbstractThesemethodshavefacilitatedimportantreal-worldappli-cationsandachievedim...
TheIntrinsicRobustnessofStochasticBanditstoStrategicManipulationZheFeng1DavidC.Parkes1HaifengXu2Abstractabletomodulateitsownrewardfeedbackinordertofurtheritsownobjective,e.g.,increasingthenumberoft...
TheImplicitRegularizationofStochasticGradientFlowforLeastSquaresAlnurAli1EdgarDobriban2RyanJ.Tibshirani3Abstractgeneratedbysequentialoptimizationalgorithmsmayserveascheapapproximationstothemoreexpe...
StructureAdaptiveAlgorithmsforStochasticBanditsRe´myDegenne1HanShao2WouterM.Koolen3Abstractstartingwithasymptoticresultsinthe80sand90s(Lai&Robbins,1985;Graves&Lai,1997)andmovingtothefi-Westudyrewa...
StochasticRegretMinimizationinExtensive-FormGamesGabrieleFarina1ChristianKroer2TuomasSandholm1345AbstractTypically,EFGmodelsareoperationalizedbycomputingeitheraNashequilibriumofthegame,oranapproxim...
StochasticSubspaceCubicNewtonMethodFilipHanzely1NikitaDoikov2PeterRichta´rik1YuriiNesterov2Abstractareinterestedintheregimewherethedimensiondisverylarge,whicharisesinmanycontexts,suchasthetraining...
StochasticLatentResidualVideoPredictionJean-YvesFranceschi1EdouardDelasalles1MickaëlChen1SylvainLamprier1PatrickGallinari12AbstractRecurrentNeuralNetworks(RNNs),whereeachgeneratedframeisfedbacktot...
StochasticOptimizationforNon-convexInf-ProjectionProblemsYanYan1YiXu2LiijunZhang3XiaoyuWang4TianbaoYang1AbstractX→Rmisalower-semicontinuousdifferentiablemapping,and·,·istheinnerproduct.Therequir...
StochasticOptimizationforRegularizedWassersteinEstimatorsMarinBallu1QuentinBerthet2FrancisBach3Abstractcantransportmasswithdistributionmeasureµtoanotherdistributionmeasureν,withminimalglobaltrans...
StochasticGradientandLangevinProcessesXiangCheng1DongYin1PeterBartlett1MichaelJordan1AbstractrestrictedtoisotropicGaussiannoise,whereasthenoiseinSGDcanbefarfromGaussian.Second,thenoisedependsWeprov...