OntheGeneralizationofEquivarianceandConvolutioninNeuralNetworkstotheActionofCompactGroupsRisiKondor1ShubhenduTrivedi2AbstractRecently,therehasbeenconsiderableinterestinextendingneuralnetworkstomore...
ObfuscatedGradientsGiveaFalseSenseofSecurity:CircumventingDefensestoAdversarialExamplesAnishAthalye1NicholasCarlini2DavidWagner2Abstractapparentrobustnessagainstiterativeoptimizationattacks:obfusca...
LocalConvergencePropertiesofSAGA/Prox-SVRGandAccelerationClaricePoon1JingweiLiang1Carola-BibianeScho¨nlieb1Abstractcientlyoutputsolutionswhichtakeacertainstructure;seeforinstance(Liangetal.,2017)f...
LimitsofEstimatingHeterogeneousTreatmentEffects:GuidelinesforPracticalAlgorithmDesignAhmedM.Alaa1MihaelavanderSchaar123Abstractadvertising(Bottouetal.,2013),andsocialsciences(Xieetal.,2012).Theincr...
LearningSteady-StatesofIterativeAlgorithmsoverGraphsHanjunDai1ZornitsaKozareva2BoDai1AlexanderJ.Smola2LeSong13Abstracttheresultsoftheaggregationoperator.Moregenerally,theintermediaterepresentationh...
LearningDynamicsofLinearDenoisingAutoencodersArnuPretorius12SteveKroon12HermanKamper3AbstractLarsson,2017),tonamejustafewareas.Denoisingau-toencoders(DAEs)areanextensionofautoencoderswhichDenoising...
LearningaMixtureofTwoMultinomialLogitsFlavioChierichetti1RaviKumar2AndrewTomkins2Abstractnoknownpolynomial-timealgorithmstolearn(exactlyorapproximately)anynon-trivialmixtureofmultinomiallo-Theclass...
InvarianceofWeightDistributionsinRectifiedMLPsRussellTsuchida1FarbodRoosta-Khorasani23MarcusGallagher1Abstractplicationratherthananunderstandingofthecapabilitiesandtrainingofneuralnetworks.Recently...
ImprovingthePrivacyandAccuracyofADMM-BasedDistributedAlgorithmsXueruZhang1MohammadMahdiKhalili1MingyanLiu1Abstractinteractiveprocessoflocalcomputationandmessagepass-ing,whichideallyshouldresultinal...
ImprovedTrainingofGenerativeAdversarialNetworksusingRepresentativeFeaturesDuhyeonBang1HyunjungShim1Abstractapplications,includingsuper-resolution,colorization,facegeneration,imagecompletion,etc.(Ba...
ImportanceWeightedTransferofSamplesinReinforcementLearningAndreaTirinzoni1AndreaSessa1MatteoPirotta2MarcelloRestelli1Abstracttions,parameters,policies,etc.)andinthecriteriausedtoestablishwhethersuc...
GlobalConvergenceofPolicyGradientMethodsfortheLinearQuadraticRegulatorMaryamFazel1RongGe2ShamM.Kakade1MehranMesbahi1Abstract2016)andAtarigameplaying(Mnihetal.,2015).Deepreinforcementlearning(DeepRL...
FastMaximizationofNon-Submodular,MonotonicFunctionsontheIntegerLatticeAlanKuhnle1J.DavidSmith1VictoriaG.Crawford1MyT.Thai1AbstractKempe,2011;Horel&Singer,2016).Inthiswork,weTheoptimizationofsubmodu...
ExploitingthePotentialofStandardConvolutionalAutoencodersforImageRestorationbyEvolutionarySearchMasanoriSuganuma12MeteOzay2TakayukiOkatani21Abstractthelimitationofthesehand-designedorsimplepriors,a...
EstimationofMarkovChainviaRank-ConstrainedLikelihoodXudongLi1MengdiWang1AnruZhang2AbstractofMarkovchainswithlow-ranktransitionmatricesinthispaper.Low-ranknessisubiquitousinpractice.Forexam-Thispape...
EquivalenceofMulticategorySVMandSimplexConeSVM:FastComputationsandStatisticalTheoryGuillaumeA.Pouliot1AbstractattemptshavebeenmadeatextendingthemethodologytoaccommodateclassificationwithK>2categori...
Entropy-SGDoptimizesthepriorofaPAC-Bayesbound:GeneralizationpropertiesofEntropy-SGDanddata-dependentpriorsGintareKarolinaDziugaite12DanielM.Roy32Abstractstochasticgradientdescent(SGD),oneoftheworkh...
DynamicalIsometryandaMeanFieldTheoryofRNNs:GatingEnablesSignalPropagationinRecurrentNeuralNetworksMinminChen1JeffreyPennington2SamuelS.Schoenholz2Abstracttion(Gravesetal.,2013)andrecommendationsyst...