ScalingMulti-AgentReinforcementLearningwithSelectiveParameterSharingFilipposChristianos1GeorgiosPapoudakis1ArrasyRahman1StefanoV.Albrecht1Abstract(e.g.(Guptaetal.,2017))wherebyagentssharesomeorallp...
Data-DependentDifferentiallyPrivateParameterLearningforDirectedGraphicalModelsAmritaRoyChowdhury1TheodorosRekatsinas1SomeshJha12AbstractHence,learningandpubliclyreleasingtheParametersoftheprobabili...
ParameterEfficientTrainingofDeepConvolutionalNeuralNetworksbyDynamicSparseReParameterizationHeshamMostafa1XinWang12Abstract1.IntroductionModerndeepneuralnetworksaretypicallyhighlyDeepneuralnetworks...
COMIC:Multi-viewClusteringWithoutParameterSelectionXiPeng1ZhenyuHuang1JianchenLv1HongyuanZhu2JoeyTianyiZhou3Abstractglesource(Hockingetal.,2011;Elhamifar&Vidal,2013;Liuetal.,2016;Flammarion,Nicolas...
Deepk-Means:Re-TrainingandParameterSharingwithHarderClusterAssignmentsforCompressingDeepConvolutionsJunruWu1YueWang2ZhenyuWu1ZhangyangWang1AshokVeeraraghavan2YingyanLin2Abstract1.IntroductionThecur...
ApproximateLeave-One-OutforFastParameterTuninginHighDimensionsShuaiwenWang1WendaZhou1HaihaoLu2ArianMaleki1VahabMirrokni3Abstractschemes,especiallyinhigh-dimensionalsettings,studiesthefollowingoptim...