UnbalancedminibatchOptimalTransport;applicationstoDomainAdaptationKilianFatras1ThibaultSe´journe´2NicolasCourty1Re´miFlamary3Abstractneedsgoodstatisticalestimationpropertiesandoptimiza-tionguara...
TestingGroupFairnessviaOptimalTransportProjectionsNianSi1KarthyekMurthy2JoseBlanchet1VietAnhNguyen13AbstractAnaturalfirstexplanationforthereportedalgorithmicbi-asesisthatthedatausedtotrainthealgori...
ScalableOptimalTransportinHighDimensionsforGraphDistances,EmbeddingAlignment,andMoreJohannesKlicpera1MartenLienen1StephanGünnemann1Abstractcostw.r.t.somepointwisecostfunction(e.g.theEuclideandista...
PrivateStochasticConvexOptimization:OptimalRatesin1GeometryHilalAsi1VitalyFeldman2TomerKoren3KunalTalwar2AbstractInthisproblem(DP-SCO),givenni.i.d.samplesz1,...,znfromadistributionP,wewishtorelease...
PAGE:ASimpleandOptimalProbabilisticGradientEstimatorforNonconvexOptimizationZhizeLi1HongyanBao1XiangliangZhang1PeterRichta´rik1Abstract(Jain&Kar,2017).Drivenbytheappliedsuccessofdeepneuralnetworks...
Outlier-RobustOptimalTransportDebarghyaMukherjee12AritraGuha3JustinSolomon42YuekaiSun1MikhailYurochkin52Abstract(e.g.d-divergences),Optimaltransportuniquelydependsonthegeometryofthesamplespace(thro...
OptimalTransportKernelsforSequentialandParallelNeuralArchitectureSearchVuNguyen∗1TamLe∗2MakotoYamada23MichaelA.Osborne4Abstractreaderstothesurvey(Elskenetal.,2019b)foradetailedreviewofNASandtothe...
OptimalThompsonSamplingstrategiesforsupport-awareCVaRbanditsDorianBaudry1RomainGautron23EmilieKaufmann1Odalric-AmbrymMaillard1AbstractValueatRisk(CVaR)aswellasmoregenericcoherentspec-tralriskmeasur...
OptimalStreamingAlgorithmsforMulti-ArmedBanditsTianyuanJin1KekeHuang1JingTang2XiaokuiXiao1Abstractson,1933),onlineadvertisement(Bertsimas&Mersereau,2007),andcrowdsourcing(Zhouetal.,2014).Ittypicall...
OptimalregretalgorithmforPseudo-1dBanditConvexOptimizationAadirupaSaha1NagarajanNatarajan2PraneethNetrapalli23PrateekJain23Abstracttheproblemhasa"pseudo-1d"structureinthelossfunc-tionsft(w)=t(gt(w;...
OptimalNon-ConvexExactRecoveryinStochasticBlockModelviaProjectedPowerMethodPengWang1HuikangLiu2ZiruiZhou3AnthonyMan-ChoSo1Abstractmodel(SBM),whichtendstogenerategraphscontainingunderlyingcommunitys...
OptimalOff-PolicyEvaluationfromMultipleLoggingPoliciesNathanKallus1YutaSaito1MasatoshiUehara1AbstractInmostoftheabovestudies,theobservationsusedtoevalu-ateanewpolicyareassumedgeneratedbyasinglelogg...
OptimalEstimationofHighDimensionalSmoothAdditiveFunctionBasedonNoisyObservationsFanZhou,PingLiCognitiveComputingLabBaiduResearch10900NE8thStBellevueWA98004USA{fanzhou,liping11}@baidu.comAbstractana...
OptimalCounterfactualExplanationsinTreeEnsemblesAxelParmentier1ThibautVidal23Abstracttriggeredextensiveresearchonalgorithmicrecourseandcounterfactualexplanations(see,e.g.,Wachteretal.,2018;Counterf...
OptimalComplexityinDecentralizedTrainingYuchengLu1ChristopherDeSa1AbstractTable1.Designchoiceofcentralizationanddecentralizationindifferentlayersofaparallelmachinelearningsystem.TheprotocolDecentra...
NearlyOptimalReward-FreeReinforcementLearningZihanZhang1SimonS.Du2XiangyangJi1AbstractRLisexplorationforwhichtheagentneedstostrategicallyvisitnewstatestolearntransitionandrewardinformationWestudyth...
MOTS:MinimaxOptimalThompsonSamplingTianyuanJin1PanXu2JiemingShi3XiaokuiXiao1QuanquanGu2Abstractplayingthebestarmandplayingthearmaccordingtothestrategy,whichisalsocalledtheregretofabanditstrategy.Th...
LearningOptimalAuctionswithCorrelatedValuationsfromSamplesChunxueYang1XiaohuiBei1Abstractsufficientandnecessarytoguaranteenear-Optimalexpectedrevenue.Consequently,oneactivelineofresearchappliesInsi...
FOP:FactorizingOptimalJointPolicyofMaximum-EntropyMulti-AgentReinforcementLearningTianhaoZhang1YuehengLi1ChenWang1GuangmingXie1ZongqingLu1Abstractvalue-basedandactor-criticMARLmethods,whereglobalin...
DifferentiableParticleFilteringviaEntropy-RegularizedOptimalTransportAdrienCorenflos1JamesThornton2GeorgeDeligiannidis2ArnaudDoucet2Abstractprocess(Xt)t≥1andY-valuedobservations(Yt)t≥1satis-fying...
