WhenDoesDataAugmentationHelpwithMembershipInferenceAttacks?YigitcanKaya1TudorDumitras,1Abstractetal.,2018;Shokrietal.,2017).Inparticular,thisenablesmembershipinferenceattacks(MIAs)tofindoutwhetherD...
RandomizedAlgorithmsforSubmodularFunctionMaximizationwithak-SystemConstraintShuangCui1KaiHan1TianshuaiZhu1JingTang2BenweiWu1HeHuang3Abstractsourcing(Singlaetal.,2016;Hanetal.,2018a),cluster-ing(Gom...
QuantumAlgorithmsforReinforcementLearningwithaGenerativeModelDaochenWang1AarthiSundaram2RobinKothari2AshishKapoor3MartinRoetteler2Abstractfasteralgorithmsforcertaintaskslikesearchandfactor-ing(Grov...
PsiPhi-Learning:ReinforcementLearningwithDemonstrationsusingSuccessorFeaturesandInverseTemporalDifferenceLearningAngelosFilos1ClareLyle1YarinGal1SergeyLevine2NatashaJaques23GregoryFarquhar4Abstract...
ProximalCausalLearningwithKernels:Two-StageEstimationandMomentRestrictionAfsanehMastouri1YuchenZhu1LimorGultchin23AnnaKorba4RicardoSilva1MattJ.Kusner1ArthurGretton†1KrikamolMuandet†5AbstractGoalA...
ProvablyCorrectOptimizationandExplorationwithNon-linearPoliciesFeiFeng1WotaoYin1AlekhAgarwal2LinYang3Abstractrer&Geist,2014;Geistetal.,2019;Abbasi-Yadkorietal.,2019;Agarwaletal.,2020c;Bhandari&Russ...
ProbabilisticProgramswithStochasticConditioningDavidTolpin1YuanZhou2TomRainforth3HongseokYang4Abstracttheprobability(massordensity)oftheobservationgiventhedistributionisusedininference(Carpentereta...
Privacy-PreservingFeatureSelectionwithSecureMultipartyComputationXilingLi1RafaelDowsley2MartineDeCock13Abstractnature.ProtectionofuserdatahasbecomeasignificantconcerninMLmodeldevelopmentanddeployme...
Privacy-PreservingVideoClassificationwithConvolutionalNeuralNetworksSikhaPentyala1RafaelDowsley2MartineDeCock13AbstractMeinich-Bacheetal.,2020;Pengetal.,2020;Shahetal.,2019;Wuetal.,2019).Manyexisti...
PrincipalBitAnalysis:AutoencodingwithSchur-ConcaveLossSourbhBhadane1AaronB.Wagner1JayadevAcharya1Abstractandgareselectedthroughtrainingfromtheclassoffunc-Weconsideralinearautoencoderinwhichthetions...
Post-SelectionInferencewithHSIC-LassoTobiasFreidling1BenjaminPoignard23He´ctorClimente-Gonza´lez3MakotoYamada34AbstractThemoststraightforwardremedyissamplesplitting,whichusesonepartofthedataformo...
Poolingformer:LongDocumentModelingwithPoolingAttentionHangZhang12YeyunGong3YelongShen4WeishengLi5JianchengLv1NanDuan3WeizhuChen4Abstract(a)Single-levellocalattention(b)Two-levelpoolingattentionInth...
PolicyCacheswithSuccessorFeaturesMarkNemecek1RonaldParr1Abstracttaskswhichvaryintheirrewardfunctions,butwherethedynamicsremainthesame.Althoughlimitedinscope,thisTransferinreinforcementlearningisbas...
PointwiseBinaryClassificationwithPairwiseConfidenceComparisonsLeiFeng1SenlinShu2NanLu34BoHan54MiaoXu64GangNiu4BoAn7MasashiSugiyama43Abstractweaklysupervisedlearningproblems(Zhou,2018)havebeenextens...
Perceiver:GeneralPerceptionwithIterativeAttentionAndrewJaegle1FelixGimeno1AndrewBrock1AndrewZisserman1OriolVinyals1JoaoCarreira1AbstractOneglaringissuewithstrongarchitecturalpriorsisthattheyareofte...
PC-MLP:Model-basedReinforcementLearningwithPolicyCoverGuidedExplorationYudaSong1WenSun2Abstractsuccessrate0.5HandEgg0.4Model-basedReinforcementLearning(RL)isa0.3DeepPC-MPL200000popularlearningparad...
PACOH:Bayes-OptimalMeta-LearningwithPAC-GuaranteesJonasRothfuss1VincentFortuin1MartinJosifoski2AndreasKrause1Abstractmeta-trainingtargettrainingtargettestingMeta-learningcansuccessfullyacquireusefu...
OptimizingBlack-boxMetricswithIterativeExampleWeightingGaurushHiranandani†1JatinMathur1HarikrishnaNarasimhan2MahdiMilaniFard2OluwasanmiKoyejo31Abstractwherethegoalistooptimizeanunknownclassificati...
OnlineSubmodularResourceAllocationwithApplicationstoRebalancingSharedMobilitySystemsPierGiuseppeSessa1IlijaBogunovic1AndreasKrause1MaryamKamgarpour1Abstracttion(i.e.,thequalitymeasureofagivenalloca...
OnlineUnrelatedMachineLoadBalancingwithPredictionsRevisitedShiLi1JiayiXian1Abstractlearnedeasily.Aspredictionsareoftenerror-prone,ide-allytheperformanceofthealgorithmshoulddeteriorateWestudytheonli...