No-RegretAlgorithmsforCapturingEventsinPoissonPointProcessesMojmírMutný1AndreasKrause1Abstractoverthesenseddomain.Inparticular,weassumetheratefunctioncanbemodeledasamemberofareproducingInhomogene...
R2-B2:RecursiveReasoning-BasedBayesianOptimizationforNo-RegretLearninginGamesZhongxiangDai1YizhouChen1BryanKianHsiangLow1PatrickJaillet2Teck-HuaHo3Abstractadversarialmachinelearning(ML),theinteract...
No-RegretExplorationinGoal-OrientedReinforcementLearningJeanTarbouriech12EvrardGarcelon1MichalValko2MatteoPirotta1AlessandroLazaric1Abstractlengthofanepisode(i.e.,thetimetoreachthegoalstate)isunkno...
No-RegretandIncentive-CompatibleOnlineLearningRupertFreeman1DavidM.Pennock2CharaPodimata3JenniferWortmanVaughan1AbstractThestandardgoalofthelearneristooutputasequenceofpredictionsalmostasaccurateas...
Let’sbeHonest:AnOptimalNo-RegretFrameworkforZero-SumGamesEhsanAsadiKangarshahi1Ya-PingHsieh1MehmetFatihSahin1VolkanCevher1Abstractresultingdynamicsisofgreatinterestinoptimizationandbehavioralecono...