Value-at-RiskOptimizationwithGaussianProcessesQuocPhongNguyen1ZhongxiangDai1BryanKianHsiangLow1PatrickJaillet2AbstractuncertaintyinZcanbecontrolledviathemean-varianceOptimizationframework(Iwazakiet...
TheLimitsofMin-MaxOptimizationAlgorithms:ConvergencetoSpuriousNon-CriticalSetsYa-PingHsieh1PanayotisMertikopoulos23VolkanCevher4AbstractGivenanalgorithmforsolving(SP),itisthennaturaltoComparedtoord...
TheImplicitRegularizationforAdaptiveOptimizationAlgorithmsonHomogeneousNeuralNetworksBohanWang1QiMeng1WeiChen1Tie-YanLiu1Abstractprocessing(Youngetal.,2018).Inpractice,deepneuralnetworks(DNN)learne...
ReservePriceOptimizationforFirstPriceAuctionsinDisplayAdvertisingZheFeng1SébastienLahaie2JonSchneider2JinchaoYe2Abstracttimizationinfirst-price(i.e.,pay-your-bid)auctions,mo-tivatedbythefactthatal...
WhiteningandSecondOrderOptimizationBothMakeInformationintheDatasetUnusableDuringTraining,andCanReduceorPreventGeneralizationNehaS.Wadia1DanielDuckworth2SamuelS.Schoenholz2EthanDyer2JaschaSohl-Dicks...
ProvablyEfficientFictitiousPlayPolicyOptimizationforZero-SumMarkovGameswithStructuredTransitionsShuangQiu1XiaohanWei2JiepingYe1ZhaoranWang3ZhuoranYang4Abstractunderstandingofmulti-agentpolicyoptimi...
ProvablyCorrectOptimizationandExplorationwithNon-linearPoliciesFeiFeng1WotaoYin1AlekhAgarwal2LinYang3Abstractrer&Geist,2014;Geistetal.,2019;Abbasi-Yadkorietal.,2019;Agarwaletal.,2020c;Bhandari&Russ...
PrivateStochasticConvexOptimization:OptimalRatesin1GeometryHilalAsi1VitalyFeldman2TomerKoren3KunalTalwar2AbstractInthisproblem(DP-SCO),givenni.i.d.samplesz1,...,znfromadistributionP,wewishtorelease...
PrivateAdaptiveGradientMethodsforConvexOptimizationHilalAsi12JohnDuchi23AlirezaFallah41OmidJavidbakht5KunalTalwar5Abstractopingprivatevariantsofstochasticgradientdescent(SGD),wherealgorithmsguarant...
PolicyGradientBayesianRobustOptimizationforImitationLearningZaynahJaved1DanielS.Brown1SatvikSharma1JerryZhu1AshwinBalakrishna1MarekPetrik2AncaD.Dragan1KenGoldberg1Abstracthuman-designedrewardfuncti...
PODS:PolicyOptimizationviaDifferentiableSimulationMiguelZamora1MomchilPeychev1SehoonHa2MartinVechev1StelianCoros1Abstractpotentiallyunsafe.Fortunately,recentyearshaveseenexcit-ingprogressinsimulati...
OptimizationPlanningfor3DConvNetsZhaofanQiu1TingYao1Chong-WahNgo2TaoMei1Abstractstance,anensembleofLGD-3Dnetworks(Qiuetal.,2019)achieves17.88%intermsofaverageerrorintrimmedvideoItisnottrivialtoopti...
OptimizationofGraphNeuralNetworks:ImplicitAccelerationbySkipConnectionsandMoreDepthKeyuluXu1MozhiZhang2StefanieJegelka1KenjiKawaguchi3AbstracttheoreticalaspectsofGNNstounderstandtheirsuccessandlimi...
OptiDICE:OfflinePolicyOptimizationviaStationaryDistributionCorrectionEstimationJongminLee1WonseokJeon23Byung-JunLee4JoellePineau235Kee-EungKim16Abstractandthentodeploythemodelwithitsparameterfixedw...
OnlineOptimizationinGamesviaControlTheory:ConnectingRegret,PassivityandPoincare´RecurrenceYunKuenCheung1GeorgiosPiliouras2AbstracttheoryandonlineOptimization.Wepresentanovelcontrol-theoreticunders...
OntheOptimalityofBatchPolicyOptimizationAlgorithmsChenjunXiao12YifanWu3TorLittlemore4BoDai2JinchengMei12LihongLi†5CsabaSzepesvari14DaleSchuurmans12Abstractafixeddatasetofpreviouslycollectedexperie...
OnProximalPolicyOptimization’sHeavy-tailedGradientsSaurabhGarg1JoshuaZhanson2EmilioParisotto1AdarshPrasad1J.ZicoKolter2ZacharyC.Lipton1SivaramanBalakrishnan3RuslanSalakhutdinov1PradeepRavikumar1Ab...
NondeterminismandInstabilityinNeuralNetworkOptimizationCeciliaSummers1MichaelJ.Dinneen1Abstractwasteful,usingmorecomputingpower,increasingthetimerequiredforeffectiveresearch,andmakingreproducibilit...
Muesli:CombiningImprovementsinPolicyOptimizationMatteoHessel1IvoDanihelka12FabioViola1ArthurGuez1SimonSchmitt1LaurentSifre1TheophaneWeber1DavidSilver12HadovanHasselt1AbstractMedianhuman-normalizeds...
MonotonicRobustPolicyOptimizationwithModelDiscrepancyYuankunJiang1ChenglinLi2WenruiDai1JunniZou1HongkaiXiong2Abstractcontroltasks,e.g.,playingcomputergameswithhuman-levelperformance(Mnihetal.,2013;...