Dual-PathDistillation:AUnifiedFrameworktoImproveBlack-BoxAttacksYonggangZhang1YaLi2TongliangLiu3XinmeiTian1Abstract(Athalyeetal.,2018),evaluatemodelrobustness(Carlini&Wagner,2017;Moosavi-Dezfooliet...
ASimpleFrameworkforContrastiveLearningofVisualRepresentationsTingChen1SimonKornblith1MohammadNorouzi1GeoffreyHinton1AbstractFigure1.ImageNetTop-1accuracyoflinearclassifierstrainedonrepresentationsl...
ADistributionalFrameworkforDataValuationAmirataGhorbani1MichaelP.Kim1JamesZou1Abstracttrainingdataismostvaluableand,hence,mostdeservingofresourcestowardscollectionandannotation.Assuch,aprin-Shapley...
AChance-ConstrainedGenerativeFrameworkforSequenceOptimizationXianggenLiu12QiangLiu3SenSong1JianPeng2Abstractlong-rangeconstraints(e.g.,valencyconditionsinmoleculargeneration),pushingthediscretesear...
SetTransformer:AFrameworkforAttention-basedPermutation-InvariantNeuralNetworksJuhoLee12YoonhoLee3JungtaekKim4AdamR.Kosiorek15SeungjinChoi4YeeWhyeTeh1Abstract1997;Maron&Lozano-Pe´rez,1998)isanexamp...
LearntoGrow:AContinualStructureLearningFrameworkforOvercomingCatastrophicForgettingXilaiLi†1YingboZhou2TianfuWu1RichardSocher2CaimingXiong2Abstractlearningwithdeepneuralnetworks(DNNs).Whenpre-sent...
kernelPSI:aPost-SelectionInferenceFrameworkforNonlinearVariableSelectionLotfiSlim12Cle´mentChatelain1Chloe´-AgatheAzencott23Jean-PhilippeVert24Abstractthevariablestestedafterselectionarelikelytoe...
AFrameworkforBayesianOptimizationinEmbeddedSubspacesAlexanderMunteanu1AminNayebi2MatthiasPoloczek32Abstracttheobjectivefunction.Thus,itisnotsurprisingthatex-pandingBOtohigher-dimensionalsearchspace...
AConditional-Gradient-BasedAugmentedLagrangianFrameworkAlpYurtsever1OlivierFercoq2VolkanCevher1AbstractThistemplatehasalargenumberofapplicationsinma-chinelearning,signalprocessing,andcomputerscienc...
Progress&Compress:AscalableFrameworkforcontinuallearningJonathanSchwarz1JelenaLuketina2WojciechM.Czarnecki1AgnieszkaGrabska-Barwinska1YeeWhyeTeh1RazvanPascanu1RaiaHadsell1Abstractpreviouslytrainedp...
Let’sbeHonest:AnOptimalNo-RegretFrameworkforZero-SumGamesEhsanAsadiKangarshahi1Ya-PingHsieh1MehmetFatihSahin1VolkanCevher1Abstractresultingdynamicsisofgreatinterestinoptimizationandbehavioralecono...
AnIterative,Sketching-basedFrameworkforRidgeRegressionAgnivaChowdhury1JiasenYang1PetrosDrineas2Abstractsion.First,whendn,i.e.,thenumberofpredictorvari-ablesdgreatlyexceedsthenumberofobservationsn,...
AnEstimationandAnalysisFrameworkfortheRaschModelAndrewS.Lan1MungChiang2ChristophStuder3Abstractresponsetheory(IRT)model(Lord,1980),isgivenbyTheRaschmodeliswidelyusedforitemre-p(Yu,i=1)=Φ(au−di),(...
AnAlgorithmicFrameworkofVariableMetricOver-RelaxedHybridProximalExtra-GradientMethodLiShen1PengSun1YitongWang1WeiLiu1TongZhang1Abstracttimizationandconvex-concavesaddle-pointoptimization,encompasse...
ActiveTesting:AnEfficientandRobustFrameworkforEstimatingAccuracy.PhucNguyen1DevaRamanan2CharlessFowlkes1AbstractnoisyvettedSampleOracledatabaseSelectionMuchrecentworkonvisualrecognitionaimstoSystem...
AUnifiedVarianceReduction-BasedFrameworkforNonconvexLow-RankMatrixRecoveryLingxiaoWang1XiaoZhang1QuanquanGu1Abstractlaxationbasedoptimization(Srebroetal.,2004;Cande`s&Tao,2010;Rohdeetal.,2011;Recht...
ASimpleMulti-ClassBoostingFrameworkwithTheoreticalGuaranteesandEmpiricalProficiencyRonAppel1PietroPerona1Abstract(a)Old:DecisionStumps(b)New:LocalizedSimilaritiesThereisaneedforsimpleyetaccuratewhi...
ALaplacianFrameworkforOptionDiscoveryinReinforcementLearningMarlosC.Machado1MarcG.Bellemare2MichaelBowling1Abstracttheoptimalpolicyforthatrewardfunction.Inthispaperweintroduceanalgorithmforoptiondi...