ConvergenceofaStochasticGradientMethodwithMomentumforNon-SmoothNon-ConvexOptimizationVienV.Mai1MikaelJohansson1AbstractThisfunctionclassisveryrichandimportantinoptimiza-tion(Rockafellar,1982;Vial,1...
ControllingOverestimationBiaswithTruncatedMixtureofContinuousDistributionalQuantileCriticsArseniiKuznetsov1PavelShvechikov12AlexanderGrishin13DmitryVetrov13AbstractThrun&Schwartz(1993)elucidatetheo...
ConsistentStructuredPredictionwithMax-MinMarginMarkovNetworksAlexNowak-Vila1FrancisBach1AlessandroRudi1Abstractdictionmistakesarenotequallycostly.Insequencepre-diction,forinstance,thenumberofpossib...
Compressivesensingwithun-trainedneuralnetworks:GradientdescentfindsthesmoothestapproximationReinhardHeckel1MahdiSoltanolkotabi2Abstractopposedtotrainedconvolutionalneuralnetworks,thatlearnanimagepr...
Multi-ObjectiveMoleculeGenerationusingInterpretableSubstructuresWengongJin1ReginaBarzilay1TommiJaakkola1Abstractwithsubstructures(e.g.,functionalgroupsorlaterpieces)thatdrivespecificpropertiesofint...
FetchSGD:Communication-EfficientFederatedLearningwithSketchingDanielRothchild∗1AshwineePanda∗1EnayatUllah2NikitaIvkin3IonStoica1VladimirBraverman2JosephGonzalez1RamanArora2Abstract2018).Evenwitho...
Communication-EfficientDistributedStochasticAUCMaximizationwithDeepNeuralNetworksZhishuaiGuo1MingruiLiu1ZhuoningYuan1LiShen2WeiLiu2TianbaoYang1Abstract1.IntroductionInthispaper,westudydistributedal...
CollaborativeMachineLearningwithIncentive-AwareModelRewardsRachaelHweeLingSim1YehongZhang1MunChoonChan1BryanKianHsiangLow1Abstractfromotherhospitalsandfirmstoimprovethepredictionofsomediseaseprogre...
Clinician-in-the-LoopDecisionMaking:ReinforcementLearningwithNear-OptimalSet-ValuedPoliciesShengpuTang1AdityaModi1MichaelW.Sjoding23JennaWiens1Abstractrewardsignalsviarewardshaping(Lizotteetal.,201...
CausalInferenceusingGaussianProcesseswithStructuredLatentConfoundersSamWitty1KentaTakatsu1DavidJensen1VikashMansinghka2Abstractwhileproducingdifferentestimatesoftheeffectsofanin-tervention.Thisobse...
BoXHED:BoostedeXactHazardEstimatorwithDynamiccovariatesXiaochenWang1ArashPakbin2BobakJ.Mortazavi2HongyuZhao1DonaldK.K.Lee3Abstractdying,butalsowhenthatmighthappen,inordertoprovidetimelycriticalcare...
BoostingDeepNeuralNetworkEfficiencywithDual-ModuleInferenceLiuLiu12LeiDeng2ZhaodongChen2YukeWang1ShuangchenLi3JingweiZhang3YihuaYang3ZhenyuGu3YufeiDing1YuanXie2Abstract2013;Heetal.,2019;Wangetal.,2...
BayesianGraphNeuralNetworkswithAdaptiveConnectionSamplingArmanHasanzadeh1EhsanHajiramezanali1ShahinBoluki1MingyuanZhou2NickDuffield1KrishnaNarayanan1XiaoningQian1Abstracttwomajorlimitations:1)theyc...
BatchReinforcementLearningwithHyperparameterGradientsByung-JunLee1JongminLee1PeterVrancx2DonghoKim2Kee-EungKim23Abstractrealenvironment.However,thisapproachrequiresalotofhumaneffortincludingdomaine...
BalancingCompetingObjectiveswithNoisyData:Score-BasedClassifiersforWelfare-AwareMachineLearningEstherRolf1MaxSimchowitz1SarahDean1LydiaT.Liu1DanielBjo¨rkegren2MoritzHardt1JoshuaBlumenstock3Abstrac...
BanditswithAdversarialScalingThodorisLykouris1VahabMirrokni2RenatoPaesLeme2AbstractModelingthisproblem,onesoonrealizesthatthetwoclas-sicalmulti-armedbanditapproachesfailtocapturetheWestudyadversari...
Continuous-TimeBayesianNetworkswithClocksNicolaiEngelmann1DominikLinzner1HeinzKoeppl12Abstractfollowafixedparametrizationthathinderstheirexpressive-ness,oraredefinedindiscretetimeasDynamicBayesianS...
ApproximatingStackedandBidirectionalRecurrentArchitectureswiththeDelayedRecurrentNeuralNetworkJavierS.Turek1ShaileeJain2VyA.Vo1MihaiCapota˘1AlexanderG.Huth23TheodoreL.Willke1Abstractelement.Howeve...
AmortizedPopulationGibbsSamplerswithNeuralSufficientStatisticsHaoWu1HeikoZimmermann1EliSennesh1TuanAnhLe2Jan-WillemvandeMeent1Abstractmakedata-efficientinferencesaboutinstance-levelvariables(e.g.ob...
AdversarialNeuralPruningwithLatentVulnerabilitySuppressionDivyamMadaan1JinwooShin23SungJuHwang134Abstractever,DNNsareextremelybrittletocarefullycraftedimper-ceptibleadversarialperturbationsintentio...