RNNwithParticleFlowforProbabilisticSpatio-temporalforecastingSoumyasundarPal†1LihengMa†1YingxueZhang2MarkCoates1Abstract2016;Kipf&Welling,2017).Recentworksestablishthatgraph-basedspatio-temporalm...
RevisitingPeng’sQ(λ)forModernReinforcementLearningTadashiKozuno1YunhaoTang2MarkRowland3Re´miMunos4StevenKapturowski3WillDabney3MichalValko4DavidAbel3Abstract1996;Watkins,1989;Peng&Williams,1994;...
RepresentationMatters:OfflinePretrainingforSequentialDecisionMakingMengjiaoYang1OfirNachum1AbstractFigure1.Asummaryoftheadvantagesofrepresentationlearningviacontrastiveself-prediction,acrossavariet...
RelativePositionalEncodingforTransformerswithLinearComplexityAntoineLiutkus1OndrˇejC´ıfka2Shih-LunWu345UmutS¸ims¸ekli6Yi-HsuanYang35Gae¨lRichard2AbstractFigure1.Examplesofattentionpatternsobs...
ReinforcementLearningforCost-AwareMarkovDecisionProcessesWesleyA.Suttle1KaiqingZhang2ZhuoranYang3DavidN.Kraemer1JiLiu4Abstractquentlyusedinpractice.Nevertheless,alternativeobjectiveshaveseenincreas...
WhittleNetworks:ADeepLikelihoodModelforTimeSeriesZhongjieYu1FabrizioVentola1KristianKersting12Abstract2015).Consider,e.g.,thestockpricechangesofindus-trialsectorsshowninFig.1(Left).Thedropinlate201...
WhiteningforSelf-SupervisedRepresentationLearningAleksandrErmolov1AliaksandrSiarohin1EnverSangineto1NicuSebe1Abstractofwordsinasentenceisusedtolearnalanguagemodel(Mikolovetal.,2013a;b;Devlinetal.,2...
RandomizedAlgorithmsforSubmodularFunctionMaximizationwithak-SystemConstraintShuangCui1KaiHan1TianshuaiZhu1JingTang2BenweiWu1HeHuang3Abstractsourcing(Singlaetal.,2016;Hanetal.,2018a),cluster-ing(Gom...
QuantumAlgorithmsforReinforcementLearningwithaGenerativeModelDaochenWang1AarthiSundaram2RobinKothari2AshishKapoor3MartinRoetteler2Abstractfasteralgorithmsforcertaintaskslikesearchandfactor-ing(Grov...
QuantileBanditsforBestArmsIdentificationMengyanZhang12ChengSoonOng21AbstractMean0.5-QuantileMean0.8-QuantileWeconsideravariantofthebestarmidentifica-A3.503.50C1.452.33tiontaskinstochasticmulti-arme...
QuantizationAlgorithmsforRandomFourierFeaturesXiaoyunLi,PingLiCognitiveComputingLabBaiduResearch10900NE8thStBellevueWA98004USA{lixiaoyun996,pingli98}@gmail.comAbstract1.IntroductionThemethodofrando...
Puttingthe“Learning”intoLearning-AugmentedAlgorithmsforFrequencyEstimationElbertDu12FranklynWang12MichaelMitzenmacher2AbstractbyθandanalgorithmAInlearning-augmentedalgorithms,algorithmsmaxM(θ,A...
ProvablyStrictGeneralisationBenefitforEquivariantModelsBrynElesedy1SheheryarZaidi2AbstractasSokolicetal.(2017);Sannai&Imaizumi(2019),coveronlytheworstcaseperformanceofalgorithms.TheseworksItiswidel...
ProvablyEfficientReinforcementLearningforDiscountedMDPswithFeatureMappingDongruoZhou1JiafanHe1QuanquanGu1Abstractlinearfunctionsorneuralnetworkstomapstatesandactionstoalow-dimensionalspaceandsolvet...
ProvablyEfficientFictitiousPlayPolicyOptimizationforZero-SumMarkovGameswithStructuredTransitionsShuangQiu1XiaohanWei2JiepingYe1ZhaoranWang3ZhuoranYang4Abstractunderstandingofmulti-agentpolicyoptimi...
ProvablyEfficientAlgorithmsforMulti-ObjectiveCompetitiveRLTianchengYu1YiTian1JingzhaoZhang1SuvritSra1Abstractaveragereturntoatargetsetsmallaslongasthissetsatisfiesaconditioncalledapproachability(Bl...
ProvableRobustnessofAdversarialTrainingforLearningHalfspaceswithNoiseDifanZou1SpencerFrei2QuanquanGu1AbstractToformalizetheabovecomment,letusdefinethero-Weanalyzethepropertiesofadversarialtrain-bus...
ProvableLipschitzCertificationforGenerativeModelsMattJordan1AlexandrosG.Dimakis1Abstractthroughavarietyofnonlinearoperatorsandrelatethistoa2-dimensionalgeometricproblemthatwesolveop-Wepresentascala...
PROGRAML:AGraph-basedProgramRepresentationforDataFlowAnalysisandCompilerOptimizationsChrisCummins1ZachariasV.Fisches2TalBen-Nun2TorstenHoefler2MichaelO’Boyle3HughLeather1AbstractInputProgramOutput...