OnlineBayesianMomentMatchingbasedSATSolverHeuristicsHaonanDuan12SaeedNejati1GeorgeTrimponias3PascalPoupart12VijayGanesh1Abstractsuchasverification(Bradley,2011),testing(Cadaretal.,2008),security(Av...
No-RegretandIncentive-CompatibleOnlineLearningRupertFreeman1DavidM.Pennock2CharaPodimata3JenniferWortmanVaughan1AbstractThestandardgoalofthelearneristooutputasequenceofpredictionsalmostasaccurateas...
NaiveExplorationisOptimalforOnlineLQRMaxSimchowitz1DylanJ.Foster2Abstractdevelopanon-asymptotictheoryofdata-drivencontinuouscontrol,withanemphasisonunderstandingkeyalgorithmicWeconsidertheproblemof...
LogarithmicRegretforAdversarialOnlineControlDylanJ.Foster1MaxSimchowitz2Abstractbyawell-behavedstochasticprocessordrivenbyaworst-caseprocesstowhichthelearnermustremainrobustinWeintroduceanewalgorit...
InformationParticleFilterTree:AnOnlineAlgorithmforPOMDPswithBelief-BasedRewardsonContinuousDomainsJohannesFischer12ÖmerS¸ahinTas¸12Abstractpadimitriou&Tsitsiklis,1987).Inreal-worldapplications,p...
Gradient-freeOnlineLearninginGameswithDelayedRewardsAmélieHéliou1PanayotisMertikopoulos21ZhengyuanZhou3AbstractSimilarissuesalsoariseinoperationsresearch,Onlinemachinelearning,andotherfieldswhere...
FormulaZero:DistributionallyRobustOnlineAdaptationviaOfflinePopulationSynthesisAmanSinha1MatthewO’Kelly2HongruiZheng2RahulMangharam2JohnDuchi1RussTedrake3Abstractdel’Automobile,2019).Empirically,...
Feature-map-levelOnlineAdversarialKnowledgeDistillationInseopChung1SeongUkPark1JanghoKim1NojunKwak1Abstractsuchasmobileorembeddedsystems.Toovercomethisissue,manyresearcheshavebeenconductedtodevelop...
DualMirrorDescentforOnlineAllocationProblemsSantiagoBalseiro12HaihaoLu2VahabMirrokni2Abstracttherequest(Talluri&vanRyzin,2004).Insearchadvertis-ing,eachtimeausermakesasearch,thesearchenginehasWecon...
DistributedOnlineOptimizationoveraHeterogeneousNetworkNimaEshraghi1BenLiang1Abstract2013),networking(Shietal.,2018),andmachinelearning(Shalev-Shwartz,2012).IndistributedOnlineoptimizationoveracom-p...
CustomizingMLPredictionsForOnlineAlgorithmsKeertiAnand1RongGe1DebmalyaPanigrahi1AbstractThekeytothisquestionistheobservationthatunlikeinagenericlearningsetting,wearenotinterestedintraditionalApopul...
BudgetedOnlineInfluenceMaximizationPierrePerrault123JenniferHealey1ZhengWen4MichalValko43Abstractencemaximization(OIM)(Vaswanietal.,2015;Wenetal.,2017)whereanagentactivelylearnsaboutthenetworkbyWei...
TowardControllingDiscriminationinOnlineAdAuctionsL.ElisaCelis1AnayMehrotra2NisheethK.Vishnoi3Abstracttheadvertiserischarged(Muthukrishnan,2009;Yuanetal.,2012;Varian,2007).Asitisnotpracticalforadver...
SurrogateLossesforOnlineLearningofStepsizesinStochasticNon-ConvexOptimizationZhenxunZhuang1AshokCutkosky2FrancescoOrabona13Abstractstepsizeηt>0.Inordertoachieveafastconvergence,thestepsizesmustbec...
OnlineVarianceReductionwithMixturesZalánBorsos1SebastianCuri1KfirY.Levy1AndreasKrause1AbstractWhymixtures?Themajorityofexistingworksonadap-tivesamplingdistributionsareunabletoexploitsimilaritiesAd...
OnlinelearningwithkernellossesAldoPacchiano1NiladriS.Chatterji1PeterL.Bartlett1Abstracttheendofeachround.Another,morechallengingfeedbackmodelisthepartialinformationorbanditfeedbackmodelWepresentage...
OnlineMeta-LearningChelseaFinn1AravindRajeswaran2ShamKakade2SergeyLevine1Abstractsettingwheretasksarerevealedoneafteranother,butaimstoattainzero-shotgeneralizationwithoutanytask-specificAcentralcap...
OnlineLearningwithSleepingExpertsandFeedbackGraphsCorinnaCortes1GiuliaDeSalvo1ClaudioGentile1MehryarMohri12ScottYang3AbstractworkforOnlinelearningwheretheactionlossesthatareobservabletothelearnerar...
OnlineConvexOptimizationinAdversarialMarkovDecisionProcessesAvivRosenberg1YishayMansour12AbstractWeproposeanovelalgorithmfortheadversarialMDPmodelwherethetransitionfunctionisunknowntotheWeconsidero...