LinearBanditswithStochasticDelayedFeedbackClaireVernade1AlexandraCarpentier2TorLattimore1GiovanniZappella3BeyzaErmis3MichaelBrueckner3Abstractmostadoptedastheyallowtotakeintoaccountthestructureofth...
LearningfromDelayedOutcomesviaProxieswithApplicationstoRecommenderSystemsTimothyA.Mann1SvenGowal1AndrásGyörgy1RayJiang1HuiyiHu1BalajiLakshminarayanan1PravSrinivasan1Abstracttheforecaster’smodel....
DelayedImpactofFairMachineLearningLydiaT.Liu1SarahDean1EstherRolf1MaxSimchowitz1MoritzHardt1Abstractvantagedgroupsinthepopulation(ExecutiveOfficeofthePresident,2016;Barocas&Selbst,2016).Consequentl...
BanditswithDelayed,AggregatedAnonymousFeedbackCiaraPike-Burke1ShipraAgrawal2CsabaSzepesvári34SteffenGrünewälder1AbstractoftheKpossiblearms.IntheclassicstochasticMABset-ting,theplayerimmediatelyo...
OnlineLearningwithLocalPermutationsandDelayedFeedbackOhadShamir1LiranSzlak1Abstracttiveandinsomecasesinferiortoalgorithmsnottailoredtocopewithworst-casebehavior.Indeed,anemerginglineofWeproposeanOn...