ExplorationthroughRewardBiasing:Reward-BiasedMaximumLikelihoodEstimationforStochasticMulti-ArmedBanditsXiLiu1Ping-ChunHsieh2Yu-HengHung2AnirbanBhattacharya3P.R.Kumar1Abstractandthenappliestheaction...
ExpertLearningthroughGeneralizedInverseMultiobjectiveOptimization:Models,Insights,andAlgorithmsChaoshengDong1BoZeng1Abstractthehumandecisionmaker’sdecisionswhilecannotdirectlyaccessherunderlyingde...
EnhancedPOET:Open-endedReinforcementLearningthroughUnboundedInventionofLearningChallengesandtheirSolutionsRuiWang1JoelLehman1AdityaRawal1JialeZhi1YulunLi1JeffClune2KennethO.Stanley1Abstractphistica...
DifferentiatingthroughtheFre´chetMeanAaronLou1IsayKatsman1QingxuanJiang1SergeBelongie1Ser-NamLim2ChristopherDeSa1AbstractFigure1.DepictedaboveistheFre´chetmean,µ,ofthreepoints,x1,x2,x3intheLoren...
DefensethroughDiverseDirectionsChristopherM.Bender1YangLi1YifengShi1MichaelK.Reiter1JunierB.Oliva1Abstractrentnetworkstateandthemodelisupdatedtoresisttheparticularattack.Unfortunately,thismethodisc...
ConstructiveUniversalHigh-DimensionalDistributionGenerationthroughDeepReLUNetworksDmytroPerekrestenko1StephanMu¨ller1HelmutBo¨lcskei12Abstractquence.Here,theinputlayersizeisdeterminedbythedimensi...
BetterDepth-WidthTrade-offsforNeuralNetworksthroughthelensofDynamicalSystemsVaggosChatziafratis1SaiGaneshNagarajan2IoannisPanageas2Abstractunderstandthatthenatureofcomputationdonebydeepandshallowne...
Average-CaseAccelerationthroughSpectralDensityEstimationFabianPedregosa1DamienScieur2Abstractworst-caseaverage-caseWedevelopaframeworkfortheaverage-caseSuboptimalityanalysisofrandomquadraticproblem...
StayWithMe:LifetimeMaximizationthroughHeteroscedasticLinearBanditsWithRenegingPing-ChunHsieh1XiLiu1AnirbanBhattacharya2P.R.Kumar1Abstractsuchproblems.Inthemodeling,availablechoicesarere-ferredtoas...
OptimalAuctionsthroughDeepLearningPaulDütting1ZheFeng2HarikrishnaNarasimham2DavidC.Parkes2SaiS.Ravindranath2AbstractInaseminalpieceofwork,Myersonresolvedtheoptimalauctiondesignproblemwhenthereisas...
MoreEfficientOff-PolicyEvaluationthroughRegularizedTargetedLearningAure´lienF.Bibaut1IvanaMalenica1NikosVlassis2MarkJ.vanderLaan1Abstractinference,andhasledtomanymethodologicaldevelop-ments.Oneoft...
ImprovedDynamicGraphLearningthroughFault-TolerantSparsificationChunJiangZhu1SabineStorandt2Kam-YiuLam3SongHan1JinboBi1Abstractβ∗=(β∗,···,βn∗)withGaussiannoises,i.e.,forevery1Graphsparsific...
ARSM:Augment-REINFORCE-Swap-MergeEstimatorforGradientBackpropagationthroughCategoricalVariablesMingzhangYin1YuguangYue1MingyuanZhou2Abstractzk∈{1,2,...,C}asaunivariateC-waycategoricalvari-able,and...
AnalyzingFederatedLearningthroughanAdversarialLensArjunNitinBhagoji1SupriyoChakraborty2PrateekMittal1SeraphinCalo2Abstractthetrainingofaneuralnetworkmodelisdistributedbe-tweenmultipleagents.Ineachr...
ImprovedLarge-ScaleGraphLearningthroughRidgeSpectralSparsificationDanieleCalandriello12IoannisKoutis3AlessandroLazaric4MichalValko1Abstractclustering(SC,VonLuxburg2007).Theintuitionbehindgraph-base...
LearningImportantFeaturesthroughPropagatingActivationDifferencesAvantiShrikumar1PeytonGreenside1AnshulKundaje1Abstracttionallygivingseparateconsiderationtotheeffectsofposi-tiveandnegativecontributi...
IdentifyingBestInterventionsthroughOnlineImportanceSamplingRajatSen1KarthikeyanShanmugam2AlexandrosG.Dimakis1SanjayShakkottai1AbstractHiddenVariablesMotivatedbyapplicationsincomputationalad-User-UI...
HierarchythroughCompositionwithMultitaskLMDPsAndrewM.Saxe1AdamC.Earle2BenjaminRosman23Abstractactionsforeachjointindividually(Mausam&Weld,2008).Finally,the‘tasks’performedbyanagentmaycomeinHierar...
EquivariancethroughParameter-SharingSiamakRavanbakhsh1JeffSchneider1Barnaba´sPo´czos1AbstractOurgoalistoshowthatparameter-sharingcanbeusedtoachieveequivariancetoanydiscretegroupaction.Weproposeto...
EmulatingtheExpert:InverseOptimizationthroughOnlineLearningAndreasBärmann1SebastianPokutta2OskarSchneider1Abstractmakingrecommendationsbasedonuserhistoryandstrate-gicplanningproblems,wheretheagent...
