RegularizationinDirectableEnvironmentswithApplicationtoTetrisJanMalteLichtenberg1O¨zgu¨rS¸ims¸ek1Abstractonregularization.Specifically,weproposeamodelthatintroducesabiastowardgivingallfeaturese...
RefinedComplexityofPCAwithOutliersFedorFomin1PetrGolovach1FahadPanolan1KirillSimonov1Abstractlow-rankapproximationofdatamatrixMbysolvingPrincipalcomponentanalysis(PCA)isoneoftheminimizeM−L2mostfun...
RandomWalksonHypergraphswithEdge-DependentVertexWeightsUthsavChitra1BenjaminJRaphael1Abstractbetweengroupsofproteinsinproteincomplexes(Ramadanetal.,2004;Ritzetal.,2014).Hypergraphsareusedinmachinel...
PROVEN:VerifyingRobustnessofNeuralNetworkswithaProbabilisticApproachTsui-WeiWeng1Pin-YuChen2LamM.Nguyen2MarkS.Squillante2AkhilanBoopathy1IvanOseledets3LucaDaniel1Abstractdevelopingeffectivecounterm...
QTRAN:LearningtoFactorizewithTransformationforCooperativeMulti-AgentReinforcementlearningKyunghwanSon1DaewooKim1WanJuKang1DavidHostallero1YungYi1Abstractneuralnetworks,whichcanrepresentaction-value...
ProvablyefficientRLwithRichObservationsviaLatentStateDecodingSimonS.Du1AkshayKrishnamurthy2NanJiang3AlekhAgarwal4MiroslavDud´ık2JohnLangford2Abstract2010;Lattimore&Hutter,2012).Consequently,treat...
ProjectionontoMinkowskiSumswithApplicationtoConstrainedLearningJoong-HoWon1JasonXu2KennethLange3AbstractBorwein,1993).Inmanytasks,however,theMinkowskisumisamoreappropriateorusefuloperationtoconside...
ProcessingMegapixelImageswithDeepAttention-SamplingModelsAngelosKatharopoulos12Franc¸oisFleuret12Abstract(b)Existingdeeparchitecturescannotoperateonvery(a)(c)largesignalssuchasmegapixelimagesdueto...
PredicateExchange:InferencewithDeclarativeKnowledgeZennaTavares1JavierBurroni2EdgarMinasyan3ArmandoSolarLezama1RajeshRanganath4Abstracttributionoverthreedimensionalscenes.Someformsofknowledge,sucha...
Plug-and-PlayMethodsProvablyConvergewithProperlyTrainedDenoisersErnestK.Ryu1JialinLiu1SichengWang2XiaohanChen2ZhangyangWang2WotaoYin1Abstractmeasurementsoftheimage,isencodedinf(x).Sof(x)issmallifxa...
PhasetransitioninPCAwithmissingdata:Reducedsignal-to-noiseratio,notsamplesize!NielsBruunIpsen1LarsKaiHansen1Abstract(1999)andthisformulationallowsforestimatingprincipalcomponentsinthepresenceofmiss...
OptimalTransportforstructureddatawithapplicationongraphsTitouanVayer1LaetitiaChapel1Re´miFlamary2RomainTavenard3NicolasCourty1Abstractevenimages(Bach&Harchaoui,2007).Thisworkconsiderstheproblemofc...
OptimalMinimalMarginMaximizationwithBoostingAllanGrønlund1KasperGreenLarsen1AlexanderMathiasen1Abstractstructsalinearcombinationclassifiersign(Tαtht(x)),t=1Boostingalgorithmsiterativelyproducelin...
OptimalAlgorithmsforLipschitzBanditswithHeavy-tailedRewardsShiyinLu1GuanghuiWang1YaoHu2LijunZhang1Abstractfromafixedbutunknownprobabilitydistributionassociatedwiththechosenarm.Inordertomaximizehisg...
OpenVocabularyLearningonSourceCodewithaGraph–StructuredCacheMilanCvitkovic1BadalSingh2AnimaAnandkumar1AbstractWhilecodecontainsnaturallanguagewordsandphrasesinordertobehuman–readable,codeisnotmea...
OnlineVarianceReductionwithMixturesZalánBorsos1SebastianCuri1KfirY.Levy1AndreasKrause1AbstractWhymixtures?Themajorityofexistingworksonadap-tivesamplingdistributionsareunabletoexploitsimilaritiesAd...
OnlinelearningwithkernellossesAldoPacchiano1NiladriS.Chatterji1PeterL.Bartlett1Abstracttheendofeachround.Another,morechallengingfeedbackmodelisthepartialinformationorbanditfeedbackmodelWepresentage...
OnlineLearningwithSleepingExpertsandFeedbackGraphsCorinnaCortes1GiuliaDeSalvo1ClaudioGentile1MehryarMohri12ScottYang3Abstractworkforonlinelearningwheretheactionlossesthatareobservabletothelearnerar...
OnlineControlwithAdversarialDisturbancesNamanAgarwal1BrianBullins21EladHazan21ShamM.Kakade341KaranSingh21AbstractChallenge1.Perhapsthemostimportantchallengeweaddressisindealingwitharbitrarydisturba...