Kernel-BasedReinforcementLearninginRobustMarkovDecisionProcessesShiauHongLim1ArnaudAutef2AbstractThisclassincludeskernelaveraging,k-nearest-neighbor,weightedk-nearestneighbor,Bezierpatches,linearin...
Imperceptible,Robust,andTargetedAdversarialExamplesforAutomaticSpeechRecognitionYaoQin1NicholasCarlini2IanGoodfellow2GarrisonCottrell1ColinRaffel2Abstractareknowntoexistondomainsrangingfromreinforc...
FingerprintPolicyOptimisationforRobustReinforcementLearningSupratikPaul1MichaelA.Osborne2ShimonWhiteson1Abstractacrossallpossiblesettings.Fortunately,policiescanoftenbetrainedandtestedinasimulatort...
FastRatesforakNNClassifierRobusttoUnknownAsymmetricLabelNoiseHenryW.J.Reeve1AtaKaba´n1Abstractetal.,2018).InthissettingtheclassicalkNNalgorithmisnolongerconsistent(seeSection5).Mostexistingtheoret...
DoublyRobustJointLearningforRecommendationonDataMissingNotatRandomXiaojieWang1RuiZhang1YuSun2JianzhongQi1Abstract(MNAR).Forexample,arecentstudyinsongrecommen-dationshowsthattheprobabilityofaratingb...
ConditioningbyadaptivesamplingforRobustdesignDavidH.Brookes1HahnbeomPark23JenniferListgarten4AbstractAdvancesinbiotechnology,chemistryandmachinelearningallowforthepossibilitytoimprovesuchdesigncycl...
BettergeneralizationwithlessdatausingRobustgradientdescentMatthewJ.Holland1KazushiIkeda2Abstractthedefactostandardlearningstrategyfortacklingmostma-chinelearningproblems(Kearns&Schapire,1994;Bartle...
AreGenerativeClassifiersMoreRobusttoAdversarialAttacks?YingzhenLi1JohnBradshaw23YashSharma4AbstractAdversarialtraining,whichaugmentsthetrainingdatawithadversariallyperturbedinputs,hasshownmoderates...
ActionRobustReinforcementLearningandApplicationsinContinuousControlChenTessler1YonathanEfroni1ShieMannor1AbstractTheadvantageofRobustpoliciesishighlightedwhencon-sideringimperfectmodels,acommonscen...
TowardsBinary-ValuedGatesforRobustLSTMTrainingZhuohanLi1DiHe1FeiTian2WeiChen2TaoQin2LiweiWang13Tie-YanLiu2AbstractingproblemofconventionalRNNs,longshort-termmem-ory(LSTM)(Gersetal.,1999;Hochreiter&...
SynthesizingRobustAdversarialExamplesAnishAthalye12LoganEngstrom12AndrewIlyas12KevinKwok2AbstractclassifiedasturtleclassifiedasrifleStandardmethodsforgeneratingadversarialex-classifiedasotheramples...
RobustandScalableModelsofMicrobiomeDynamicsTravisE.Gibson1GeorgK.Gerber1Abstract1.IntroductionMicrobesareeverywhere,includinginandonourThehumanmicrobiomeconstitutesallthemicroorganismsbodies,andhav...
prDeep:RobustPhaseRetrievalwithaFlexibleDeepNetworkChristopherA.Metzler1PhilipSchniter2AshokVeeraraghavan1RichardG.Baraniuk1AbstractPRalgorithmswerefirstdevelopedintheearly1970sandhavebeencontinuou...
PIPPS:FlexibleModel-BasedPolicySearchRobusttotheCurseofChaosPaavoParmas1CarlEdwardRasmussen2JanPeters34KenjiDoya1AbstractVelocityPreviously,theexplodinggradientproblemhasPositionPositionbeenexplain...
NearlyOptimalRobustSubspaceTrackingPraneethNarayanamurthy1NamrataVaswani1Abstractetal.,2011),AltProj(Netrapallietal.,2014),RPCA-GD(Yietal.,2016),NO-RMC(Cherapanamjerietal.,2016).Robustsubspacetrack...
MoreRobustDoublyRobustOff-policyEvaluationMehrdadFarajtabar1YinlamChow2MohammadGhavamzadeh2AbstractSwaminathanetal.2017)andreinforcementlearning(RL)(e.g.,Precupetal.2000a;2001;Paduraru2013;MahmoodW...
LearningtoReweightExamplesforRobustDeepLearningMengyeRen12WenyuanZeng12BinYang12RaquelUrtasun12Abstractdifferentforms.Classimbalanceinthetrainingsetisaverycommonexample.Inapplicationssuchasobjectde...
GeneralizedRobustBayesianCommitteeMachineforLarge-scaleGaussianProcessRegressionHaitaoLiu1JianfeiCai2YiWang3Yew-SoonOng24Abstractpredictivedistributionsattestpoints.InordertoscalestandardGaussianpr...
DoesDistributionallyRobustSupervisedLearningGiveRobustClassifiers?WeihuaHu12GangNiu2IsseiSato12MasashiSugiyama21AbstractDistributionallyRobustSupervisedLearning(DRSL)isapromisingparadigmtotacklethi...