ObjectiveBoundConditionalGaussianProcessforBayesianOptimizationTaewonJeong1HeeyoungKim1Abstractmationisunavailable.BOisparticularlyusefulwhentheobjectivefunctionisexpensivetoevaluate.Inthiscase,AGa...
ImprovedRegretBoundandExperienceReplayinRegularizedPolicyIterationNevenaLazic´1DongYin1YasinAbbasi-Yadkori1CsabaSzepesva´ri12AbstractproposedbyEven-Daretal.(2009),wheretheagentse-lectspoliciesbyr...
GeneralizationErrorBoundforHyperbolicOrdinalEmbeddingAtsushiSuzuki1AtsushiNitanda2JingWang1LinchuanXu3MarcCavazza1KenjiYamanishi4Abstracttheyareasconsistentaspossiblewithgivenordinaldataintheformof...
ALowerBoundfortheSampleComplexityofInverseReinforcementLearningAbiKomanduru1JeanHonorio2AbstractproblemcanbeembeddedinLMDP,solutionstostandardMDPproblemsbasedonstandardMDPsareguaranteedtoInverserei...
CLUB:AContrastiveLog-ratioUpperBoundofMutualInformationPengyuCheng1WeituoHao1ShuyangDai1JiachangLiu1ZheGan2LawrenceCarin1Abstract2015),andmachinelearning(Chenetal.,2016;Alemietal.,2016;Hjelmetal.,2...
Entropy-SGDoptimizesthepriorofaPAC-BayesBound:GeneralizationpropertiesofEntropy-SGDanddata-dependentpriorsGintareKarolinaDziugaite12DanielM.Roy32Abstractstochasticgradientdescent(SGD),oneoftheworkh...
ADivergenceBoundforHybridsofMCMCandVariationalInferenceandanApplicationtoLangevinDynamicsandSGVIJustinDomke1Abstractthem.Computingp(z)thusrequiresafullpassoverthedataset.TheideaofStochasticGradient...