ImprovedRegretBoundandExperienceReplayinRegularizedPolicyIterationNevenaLazic´1DongYin1YasinAbbasi-Yadkori1CsabaSzepesva´ri12AbstractproposedbyEven-Daretal.(2009),wheretheagentse-lectspoliciesbyr...
Improved,DeterministicSmoothingfor1CertifiedRobustnessAlexanderLevine1SoheilFeizi1Abstracthaviorofmachinelearningsystemsundersmallinputper-turbations(Szegedyetal.,2013;Goodfellowetal.,2014;Randomiz...
ImprovedRegretBoundsofBilinearBanditsusingActionSpaceAnalysisKyoungseokJang1Kwang-SungJun2Se-YoungYun3WanmoKang1Abstractarrangecouplesbasedontheirexperiencestogetbetterrat-ingsandrewards.Balancinge...
ImprovedContrastiveDivergenceTrainingofEnergy-BasedModelsYilunDu1ShuangLi1JoshuaTenenbaum1IgorMordatch2AbstractFigure1:(Left)128x128samplesonunconditionalCelebA-HQ.(Right)128x128samplesonunconditio...
ImprovedOODGeneralizationviaAdversarialTrainingandPre-trainingMingyangYi12†LuHou3JiachengSun3LifengShang3XinJiang3QunLiu3Zhi-MingMa12Abstractmanceofthemodelonthedatafromashifteddistributionaroundt...
ImprovedDenoisingDiffusionProbabilisticModelsAlexNichol1PrafullaDhariwal1AbstractandVAEs(Kingma&Welling,2013).Thisraisesvariousquestions,suchaswhetherDDPMsarecapableofcapturingDenoisingdiffusionpro...
ImprovedCorruptionRobustAlgorithmsforEpisodicReinforcementLearningYifangChen1SimonS.Du1KevinJamieson1Abstractstageaccordingtotheunderlyingtransitionfunction.Westudyepisodicreinforcementlearningunde...
ImprovedAlgorithmsforAgnosticPool-basedActiveClassificationJulianKatz-Samuels1JifanZhang2LalitJain2KevinJamieson2Abstractlearningmethodsrequirethatthisdatabelabeledandreli-ablelabelsarecostlysincet...
ImprovedConfidenceBoundsfortheLinearLogisticModelandApplicationstoBanditsKwang-SungJun1LalitJain2BlakeMason3HoussamNassif4Abstractafeaturevectorforeacharm.Acommonassumptionisthattherewardisanoisyli...
GraphConvolutionforSemi-SupervisedClassification:ImprovedLinearSeparabilityandOut-of-DistributionGeneralizationAseemBaranwal1KimonFountoulakis1AukoshJagannath2Abstractetal.,2016),andclassifyingtype...
DenseforthePriceofSparse:ImprovedPerformanceofSparselyInitializedNetworksviaaSubspaceOffsetIlanPrice12JaredTanner12Abstract1.1.CompetingPrioritiesforSparseNetworksThatneuralnetworksmaybeprunedtohig...
ClusteredSampling:Low-VarianceandImprovedRepresentativityforClientsSelectioninFederatedLearningYannFraboni12RichardVidal2LaetitiaKameni2MarcoLorenzi1Abstractsametime.Theseconsiderationsledtosignifi...
AlphaNet:ImprovedTrainingofSupernetswithAlpha-DivergenceDilinWang1ChengyueGong2MengLi1QiangLiu2VikasChandra1AbstractNeuralarchitecturesearch(NAS)automatestheneuralnet-workdesignbyexploringanenormou...
Uncertainty-AwareLookaheadFactorModelsforQuantitativeInvestingLakshayChauhan1JohnAlberg1ZacharyC.Lipton23Abstract2016;McGroartyetal.,2018).Onthescaleofdays,pricefluctuationmightbedrivenbythenewscyc...
ImprovedSleepingBanditswithStochasticActionsSetsandAdversarialRewardsAadirupaSaha1PierreGaillard2MichalValko3Abstractetal.,2012).Howeverinvariousrealworldapplications,thedecisionspace(setofarmsA)of...
ImprovedOptimisticAlgorithmsforLogisticBanditsLouisFaury12MarcAbeille1Cle´mentCalauze`nes1OlivierFercoq2Abstractetal.(2017)andreferencestherein),itspracticalinterestislimitedbythelinearstructureof...
ImprovedBoundsonMinimaxRegretunderLogarithmicLossviaSelf-ConcordanceBlairBilodeau123DylanJ.Foster4DanielM.Roy123AbstractTheloglosspenalizestheplayerbasedonhowmuchprob-abilitymasstheyplaceontheactua...
ImprovedCommunicationCostinDistributedPageRankComputation–ATheoreticalStudySiqiangLuo1AbstractNeumannetal.,2011;Ponzetto&Strube,2007).GivenagraphGofnnodesandaprobabilityα∈(0,1),thePageRankisawid...
SGD:GeneralAnalysisandImprovedRatesRobertM.Gower1NicolasLoizou2XunQian3AlibekSailanbayev3EgorShulgin4PeterRichta´rik324Abstractwhereeachfi:Rd→Rissmooth(butnotnecessarilyconvex).Further,weassumeth...
RandomMatrixImprovedCovarianceEstimationforaLargeClassofMetricsMalikTiomoko12FlorentBouchard3GuillaumeGinolhac3RomainCouillet21AbstractconstraintswithLASSOandgraphicalLASSO-basedap-proaches(Friedma...