PrivateStochasticConvexOptimization:OptimalRatesin1GeometryHilalAsi1VitalyFeldman2TomerKoren3KunalTalwar2Abstractinthisproblem(DP-SCO),givenni.i.d.samplesz1,...,znfromadistributionP,wewishtorelease...
PolicyAnalysisusingSyntheticControlsinContinuous-TimeAlexisBellot12MihaelavanderSchaar123Abstractoraverageinaneighbourhoodofcontrols)oftenprovidesamoreinformativecomparisonfortreatmenteffectestimat...
Poisson-RandomisedDirBN:LargemutationisneededinDirichletbeliefnetworksXuhuiFan1BinLi2YaqiongLi3ScottA.Sisson1Abstract1.introductionTheDirichletBeliefNetwork(DirBN)wasre-TheDirichletBeliefNetwork(Di...
ParallelDropletControlinMEDABiochipsUsingMulti-AgentReinforcementLearningTung-CheLiang1JinZhou1Yun-ShengChan2Tsung-YiHo3KrishnenduChakrabarty1Chen-YiLee2Abstract1.introductionMicrofluidicbiochipsar...
OptimalNon-ConvexExactRecoveryinStochasticBlockModelviaProjectedPowerMethodPengWang1HuikangLiu2ZiruiZhou3AnthonyMan-ChoSo1Abstractmodel(SBM),whichtendstogenerategraphscontainingunderlyingcommunitys...
OptimalCounterfactualExplanationsinTreeEnsemblesAxelParmentier1ThibautVidal23Abstracttriggeredextensiveresearchonalgorithmicrecourseandcounterfactualexplanations(see,e.g.,Wachteretal.,2018;Counterf...
OptimalComplexityinDecentralizedTrainingYuchengLu1ChristopherDeSa1AbstractTable1.Designchoiceofcentralizationanddecentralizationindifferentlayersofaparallelmachinelearningsystem.TheprotocolDecentra...
OnlineOptimizationinGamesviaControlTheory:ConnectingRegret,PassivityandPoincare´RecurrenceYunKuenCheung1GeorgiosPiliouras2Abstracttheoryandonlineoptimization.Wepresentanovelcontrol-theoreticunders...
OnlineLearninginUnknownMarkovGamesYiTian1YuanhaoWang2TianchengYu1SuvritSra1Abstractcontrolboth/allplayersandaimtominimizethenumberofepisodesrequiredtofindagoodpolicy;and(2)theonlineWestudyonlinelea...
RegretMinimizationinStochasticNon-ConvexLearningviaaProximal-GradientApproachNadavHallak1PanayotisMertikopoulos2VolkanCevher3Abstractproblems,andtheycanadapttodifferentmeasuresofregretunderdifferen...
RandomizedExplorationforReinforcementLearningwithGeneralValueFunctionApproximationHaqueIshfaq12QiwenCui3VietNguyen12AlexAyoub4ZhuoranYang5ZhaoranWang6DoinaPrecup127LinF.Yang8Abstractwhengeneralfunc...
Rate-DistortionAnalysisofMinimumExcessRiskinBayesianLearningHassanHafez-Kolahi1BehradMoniri2ShohrehKasaei1MahdiehSoleymaniBaghshah1Abstractinthisregardistostudylowerboundsontheexcessriskwhichcouldb...
OnSignal-to-NoiseRatioIssuesinVariationalinferenceforDeepGaussianProcessesTimG.J.Rudner1OscarKey2YarinGal1TomRainforth1Abstract.42WeshowthatthegradientestimatesusedinregtrainingDeepGaussianProcesse...
OnEstimationinLatentVariableModelsGuanhuaFang,PingLiCognitiveComputingLabBaiduResearch10900NE8thStBellevueWA98004USA{guanhuafang,liping11}@baidu.comAbstractvariablescanbeaggregatedinamodeltoreprese...
No-regretAlgorithmsforCapturingEventsinPoissonPointProcessesMojmírMutný1AndreasKrause1Abstractoverthesenseddomain.inparticular,weassumetheratefunctioncanbemodeledasamemberofareproducinginhomogene...
NondeterminismandinstabilityinNeuralNetworkOptimizationCeciliaSummers1MichaelJ.Dinneen1Abstractwasteful,usingmorecomputingpower,increasingthetimerequiredforeffectiveresearch,andmakingreproducibilit...
NeuralFeatureMatchinginImplicit3DRepresentationsYunluChen1BasuraFernando2HakanBilen3ThomasMensink41EfstratiosGavves1AbstractsourceappearancefeaturefittingmatchingRecently,neuralimplicitfunctionshav...
Near-OptimalModel-FreeReinforcementLearninginNon-StationaryEpisodicMDPsWeichaoMao1KaiqingZhang1RuihaoZhu2DavidSimchi-Levi2TamerBas¸ar1Abstractthroughsequentialinteractionswithaninitiallyunknownbut...
MultiplicativeNoiseandHeavyTailsinStochasticOptimizationLiamHodgkinson1MichaelW.Mahoney1Abstract(orquenching)perspective,examinesconvergenceeitherinexpectation(Chenetal.,2019;Zhouetal.,2018;GowerAl...
Muesli:CombiningImprovementsinPolicyOptimizationMatteoHessel1IvoDanihelka12FabioViola1ArthurGuez1SimonSchmitt1LaurentSifre1TheophaneWeber1DavidSilver12HadovanHasselt1AbstractMedianhuman-normalizeds...