NeuralPharmacodynamicStateSpaceModelingZeshanHussain1RahulG.Krishnan2DavidSontag1Abstractsub-type(Zhangetal.,2019b).Todothesetaskswell,under-standinghowapatient’sbiomarkersevolveovertimegivenModel...
LearningSelf-ModulatingAttentioninContinuousTimeSpacewithApplicationstoSequentialRecommendationChaoChen1HaoyuGeng12NianzuYang12JunchiYan12DaiyueXue3JianpingYu3XiaokangYang12Abstractfadeawayduetomat...
LatentSpaceEnergy-BasedModelofSymbol-VectorCouplingforTextGenerationandClassificationBoPang1YingNianWu1Abstractmostofpriormethodsfocusontheimprovementoftextgenerationqualitysuchasfluencyanddiversit...
ExplorationinApproximateHyper-StateSpaceforMetaReinforcementLearningLuisaZintgraf1LeoFeng2CongLu1MaximilianIgl1KristianHartikainen1KatjaHofmann3ShimonWhiteson1AbstractFigure1.IllustrationoftheMeta-...
FunctionalSpaceAnalysisofLocalGANConvergenceValentinKhrulkov1ArtemBabenko12IvanOseledets3Abstractousgradientdescent.InNagarajan&Kolter(2017)itwasshownthatundermildassumptions,thismethodislocallyRec...
AnInformation-GeometricDistanceontheSpaceofTasksYansongGao1PratikChaudhari2AbstractFigure1.Coupledtransferofthedataandtheconditionaldis-tribution.WesolveanoptimizationproblemthattransportstheThispa...
StateSpaceExpectationPropagation:EfficientInferenceSchemesforTemporalGaussianProcessesWilliamJ.Wilkinson1PaulE.Chang1MichaelRiisAndersen2ArnoSolin1AbstractFiltering/Forwardpass→←Smoothing/Backwar...
ReinforcementLearninginFeatureSpace:MatrixBandit,Kernels,andRegretBoundLinF.Yang1MengdiWang2Abstractplayanactiona∈A,whereSandAarethestateandactionSpaces.ThenthesystemtransitionstoanotherstateExplo...
LatentSpaceFactorisationandManipulationviaMatrixSubSpaceProjectionXiaoLi12ChenghuaLin2RuizheLi2ChaozhengWang1FrankGuerin3Abstractabsent.Neverthelesswewouldlikeoursystemtosomehowisolatetheexplanator...
BreakingtheCurseofSpaceExplosion:TowardsEffcientNASwithCurriculumSearchYongGuo1YaofoChen12YinZheng3PeilinZhao4JianChen15JunzhouHuang4MingkuiTan1AbstractStandardNASwithNASwithcurriculumsearchfixedse...
SublinearSpacePrivateAlgorithmsUndertheSlidingWindowModelJalajUpadhyay1Abstract2014a;b;Josephetal.,2018).Arelatedmodelthathasbeenstudiedwithprivacyconsiderationsisthatofcontinualre-TheDifferentialp...
DeepMDP:LearningContinuousLatentSpaceModelsforRepresentationLearningCarlesGelada1SaurabhKumar1JacobBuckman2OfirNachum1MarcG.Bellemare1Abstractlearningprocessbyreducingtheredundantandirrelevantinfor...
AWrappedNormalDistributiononHyperbolicSpaceforGradient-BasedLearningYoshihiroNagano1ShoichiroYamaguchi2YasuhiroFujita2MasanoriKoyama2Abstract(a)AtreerepresentationofthetrainingdatasetHyperbolicspac...
StateSpaceGaussianProcesseswithNon-GaussianLikelihoodHannesNickisch1ArnoSolin2AlexanderGrigorievskiy23Abstractaddressedbyapproximatecovariancecomputationsusingsparseinducingpointmethods(Quin˜onero...
Semi-SupervisedLearningviaCompactLatentSpaceClusteringKonstantinosKamnitsas12DanielC.Castro12LoicLeFolgoc2IanWalker2RyutaroTanno13DanielRueckert2BenGlocker2AntonioCriminisi1AdityaNori1AbstractFigur...
OptimizingtheLatentSpaceofGenerativeNetworksPiotrBojanowski1ArmandJoulin1DavidLopezPaz1ArthurSzlam1Abstractasto“fool”thediscriminator.Afterpropertraining,thegeneratorisabletoproducerealisticnatur...
LatentSpacePoliciesforHierarchicalReinforcementLearningTuomasHaarnoja1KristianHartikainen2PieterAbbeel1SergeyLevine1AbstractresentationsintoRListhepotentialfortheemergenceofhi-erarchies,whichcanena...
ReducedSpaceandFasterConvergenceinImperfect-InformationGamesviaPruningNoamBrown1TuomasSandholm1AbstractwasusedtoessentiallysolveLimitTexasHold’em,thelargestimperfect-informationgameevertobeessenti...
LearningLatentSpaceModelswithAngularConstraintsPengtaoXie12YuntianDeng3YiZhou4AbhimanuKumar5YaoliangYu6JamesZou7EricP.Xing2Abstractrameterizedbyaweightvector.Forinstance,inatopicmodel(Bleietal.,200...