EfficientDifferentiableSimulationofArticulatedBodiesYi-LingQiao12JunbangLiang1VladlenKoltun2MingC.Lin1Abstract2019).However,theydonothaveaccesstoanalyticderiva-tivesofthearticulateddynamics.Therefo...
EffcientDeviationTypesandLearningforHindsightRationalityinExtensive-FormGamesDustinMorrill1RyanD’Orazio2MarcLanctot3JamesR.Wright1MichaelBowling13AmyR.Greenwald4Abstractmeasuredbyregretinhindsight...
DAGswithNoCurl:AnEfficientDAGStructureLearningApproachYueYu1TianGao2NaiyuYin3QiangJi3AbstractHowever,DAGlearningisproventobeNP-hard(Chicker-ingetal.,2004)andscalabilitybecomesamajorissue.Recentlydi...
BridgingMulti-TaskLearningandMeta-Learning:TowardsEfficientTrainingandEffectiveAdaptationHaoxiangWang1HanZhao1BoLi1Abstract1.IntroductionMulti-tasklearning(MTL)aimstoimprovetheMulti-tasklearninghas...
Auto-NBA:EfficientandEffectiveSearchOvertheJointSpaceofNetworks,Bitwidths,andAcceleratorsYongganFu1YonganZhang1YangZhang2DavidCox2YingyanLin1Abstractacceleratorefficiency.Ourcodesareavailableat:htt...
BeyondtheParetoEfficientFrontier:ConstraintActiveSearchforMultiobjectiveExperimentalDesignGustavoMalkomes1BolongCheng1EricHansLee1MichaelMcCourt1AbstractInrecentyears,activelearninghasgainedpopular...
AFreeLunchFromANN:TowardsEfficient,AccurateSpikingNeuralNetworksCalibrationYuhangLi12ShikuangDeng1XinDong3RuihaoGong4ShiGu1AbstractFeaturesTrainingConversionCalibrationSpikingNeuralNetwork(SNN)hasb...
1-bitAdam:CommunicationEfficientLarge-ScaleTrainingwithAdam’sConvergenceSpeedHanlinTang12ShaoduoGan3AmmarAhmadAwan1SamyamRajbhandari1ConglongLi1XiangruLian2JiLiu2CeZhang3YuxiongHe1Abstract1.Introd...
ATaleofTwoEfficientandInformativeNegativeSamplingDistributionsShabnamDaghaghi1TharunMedini1NicholasMeisburger2BeidiChen3MengnanZhao1AnshumaliShrivastava21AbstractAIproblemsarecurrentlymodeledasmass...
StateSpaceExpectationPropagation:EfficientInferenceSchemesforTemporalGaussianProcessesWilliamJ.Wilkinson1PaulE.Chang1MichaelRiisAndersen2ArnoSolin1AbstractFiltering/Forwardpass→←Smoothing/Backwar...
StatisticallyEfficientOff-PolicyPolicyGradientsNathanKallus1MasatoshiUehara2AbstractTable1.Comparisonofoff-policypolicygradientestimators.Here,f=Θ(g)means0<liminff/g≤limsupf/g<∞(nottoPolicygradi...
SemismoothNewtonAlgorithmforEfficientProjectionsonto1,∞-normBallDejunChu1ChangshuiZhang1ShiliangSun2QingTao3AbstracttionproblemThestructuredsparsity-inducing1,∞-norm,asminL(W)+λR(W)(1)ageneraliz...
ScalableandEfficientComparison-basedSearchwithoutFeaturesDaniyarChumbalov1LucasMaystre2MatthiasGrossglauser1Abstractameaningfulquery.However,thisisoftenanon-trivialtaskforahumanuser.Forexample,most...
ProvablyEfficientModel-basedPolicyAdaptationYudaSong1AditiMavalankar1WenSun2SicunGao1AbstractMordatchetal.,2015),ormeta-learnpoliciesormodelsthatcanbequicklyadaptedtoin-distributionenvironments(Fin...
ProvablyEfficientExplorationinPolicyOptimizationQiCai1ZhuoranYang2ChiJin3ZhaoranWang1Abstractofiterations,evengiveninfinitedata.Meanwhile,fromthestatisticalperspective,itremainsunclearhowtoattainWh...
PENNI:PrunedKernelSharingforEfficientCNNInferenceShiyuLi1EdwardHanson1HaiLi1YiranChen1Abstractlayer(Zagoruyko&Komodakis,2016),ormorebranches(Szegedyetal.,2015).Amajordrawbackofna¨ıvelyin-Although...
OracleEfficientPrivateNon-ConvexOptimizationSethNeel1AaronRoth2GiuseppeVietri3ZhiweiStevenWu3Abstractandaparameterw∈W:argminwL(D,w).Thisgeneralclassofproblemsincludesclassicalempiricalriskminimiza...
OnEfficientConstructionsofCheckpointsYuChen1ZhenmingLiu1BinRen1XinJin2AbstractProducingcheckpointsfrequentlyenablesfailedtrainingprocesstorestartwithminimumwastedtime,andservesEfficientconstruction...
OnEfficientLowDistortionUltrametricEmbeddingVincentCohen-Addad1KarthikC.S.2GuillaumeLagarde3Abstract1.IntroductionAclassicprobleminunsupervisedlearningandThecurseofdimensionalityhasruthlesslybeenha...
MultiresolutionTensorLearningforEfficientandInterpretableSpatialAnalysisJungYeonPark1KennethTheoCarr1StephanZheng2YisongYue3RoseYu14AbstractWeareinterestedinlearn-Efficientandinterpretablespatialan...