ModularityinReinforcementLearningviaAlgorithmicIndependenceinCreditAssignmentMichaelChang1SidhantKaushik1SergeyLevine1ThomasL.Griffiths2Abstract1.IntroductionManytransferproblemsrequirere-usingprev...
IncentivizingCompliancewithAlgorithmicInstrumentsDanielNgo1LoganStapleton1VasilisSyrgkanis2ZhiweiStevenWu3Abstractcausaleffectsrelyonrandomizedexperiments,whichran-domlyassigneachindividualinapopul...
OntheLong-termImpactofAlgorithmicDecisionPolicies:EffortUnfairnessandFeatureSegregationthroughSocialLearningHodaHeidari1VedantNanda2KrishnaP.Gummadi2AbstractThisrealizationhasrecentlyspawnedanactiv...
AnAlgorithmicFrameworkofVariableMetricOver-RelaxedHybridProximalExtra-GradientMethodLiShen1PengSun1YitongWang1WeiLiu1TongZhang1Abstracttimizationandconvex-concavesaddle-pointoptimization,encompasse...
AlgorithmicStabilityandHypothesisComplexityTongliangLiu1Ga´borLugosi234GergelyNeu5DachengTao1AbstractHardtetal.(2015)showedthatparametricmodelstrainedbystochasticgradientdescentalgorithmsareunifor...