SequentialDomainAdaptationbySynthesizingDistributionallyRobustExpertsBaharTaskesen1Man-ChungYue2Jose´Blanchet3DanielKuhn1VietAnhNguyen34Abstractabsenceofmeaningfuldatatotuneanyparameters.How-ever,...
First-OrderMethodsforWassersteinDistributionallyRobustMDPsJulienGrand-Cle´ment1ChristianKroer1Abstractpolicies,astheyoptimizeonlyfortheworst-casekernelre-alization,withoutincorporatingdistribution...
FundamentalTradeoffsinDistributionallyAdversarialTrainingMohammadMehrabi1AdelJavanmard1RyanA.Rossi2AnupB.Rao2TungMai2Abstractperformance,andhavebeendeployedinamultitudeofap-plicationsdomainsranging...
DistributionallyRobustOptimizationwithMarkovianDataMengmengLi1TobiasSutter1DanielKuhn1Abstractrespondingtothetrainingsamplesandsolvestheresultingempiricalriskminimizationproblem(Shapiroetal.,2014)....
ActiveLearningforDistributionallyRobustLevel-SetEstimationYuInatsu1ShogoIwazaki1IchiroTakeuchi12Abstractvironmentalvariables.Thedesignvariablesarecompletelycontrollable,whereasenvironmentalvariable...
PrincipledLearningMethodforWassersteinDistributionallyRobustOptimizationwithLocalPerturbationsYongchanKwon1WonyoungKim2Joong-HoWon2MyungheeChoPaik2Abstractsothecomputationoftheriskin(1)isimpossible...
FormulaZero:DistributionallyRobustOnlineAdaptationviaOfflinePopulationSynthesisAmanSinha1MatthewO’Kelly2HongruiZheng2RahulMangharam2JohnDuchi1RussTedrake3Abstractdel’Automobile,2019).Empirically,...
DistributionallyRobustPolicyEvaluationandLearninginOfflineContextualBanditsNianSi1FanZhang1ZhengyuanZhou2JoseBlanchet1Abstractnomenonintheseapplications,canbeintelligentlyexploitedtoachievebetterou...
DoesDistributionallyRobustSupervisedLearningGiveRobustClassifiers?WeihuaHu12GangNiu2IsseiSato12MasashiSugiyama21AbstractDistributionallyRobustSupervisedLearning(DRSL)isapromisingparadigmtotacklethi...