Hilbert space embeddings and metrics on probability measures

zbMath1242.60005arXiv0907.5309MaRDI QIDQ2896088

Arthur Gretton, Bernhard Schölkopf, Kenji Fukumizu, Gert R. G. Lanckriet, Bharath K. Sriperumbudur

Publication date: 13 July 2012

Full work available at URL: https://arxiv.org/abs/0907.5309

zbMATH Keywords

weak topologykernel methodsprobability metricsindependence testshomogeneity testsuniversal kernelscharacteristic kernelsHilbertian metric

Mathematics Subject Classification ID

Probability measures on topological spaces (60B05) Convergence of probability measures (60B10) Applications of functional analysis in probability theory and statistics (46N30)

Related Items (94)

Machine learning with kernels for portfolio valuation and risk management ⋮ State-based confidence bounds for data-driven stochastic reachability using Hilbert space embeddings ⋮ A Rigorous Theory of Conditional Mean Embeddings ⋮ On the optimal estimation of probability measures in weak and strong topologies ⋮ Adaptive test of independence based on HSIC measures ⋮ Testing independence and goodness-of-fit jointly for functional linear models ⋮ On Gaussian kernels on Hilbert spaces and kernels on hyperbolic spaces ⋮ Numerical solution of fractional differential equations with temporal two-point BVPs using reproducing kernal Hilbert space method ⋮ Kernel dimension reduction in regression ⋮ Canonical kernel dimension reduction ⋮ Distribution regression model with a Reproducing Kernel Hilbert Space approach ⋮ Robust and parallel Bayesian model selection ⋮ Nonlinear and additive principal component analysis for functional data ⋮ A kernel learning framework for domain adaptation learning ⋮ Strictly proper kernel scores and characteristic kernels on compact spaces ⋮ Operator-valued positive definite kernels and differentiable universality ⋮ Learning rate of distribution regression with dependent samples ⋮ Compressive statistical learning with random feature moments ⋮ Statistical learning guarantees for compressive clustering and compressive mixture modeling ⋮ Large-scale eigenvector approximation via Hilbert space embedding Nyström ⋮ Kaplan-Meier V- and U-statistics ⋮ Principled analytic classifier for positive-unlabeled learning via weighted integral probability metric ⋮ Generalization of the energy distance by Bernstein functions ⋮ Radon-Sobolev variational auto-encoders ⋮ On the capacity of deep generative networks for approximating distributions ⋮ A one-sample test for normality with kernel methods ⋮ Near-optimal coresets of kernel density estimates ⋮ BLUE against OLSE in the location model: energy minimization and asymptotic considerations ⋮ Reproducing kernel Hilbert spaces in the mean field limit ⋮ Learning rates for the kernel regularized regression with a differentiable strongly convex loss ⋮ Bregman divergences based on optimal design criteria and simplicial measures of dispersion ⋮ EuMMD: efficiently computing the MMD two-sample test statistic for univariate data ⋮ Topology, convergence, and reconstruction of predictive states ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Domain Generalization by Functional Regression ⋮ Minimum-energy measures for singular kernels ⋮ Online MCMC Thinning with Kernelized Stein Discrepancy ⋮ On harmonic Hilbert spaces on compact abelian groups ⋮ Discrepancy-based inference for intractable generative models using quasi-Monte Carlo ⋮ Robustness and sample complexity of model-based MARL for general-sum Markov games ⋮ Convergence analysis of approximation formulas for analytic functions via duality for potential energy minimization ⋮ Stein variational gradient descent: many-particle and long-time asymptotics ⋮ Hilbert C∗-Module for Analyzing Structured Data ⋮ Characteristic kernels on Hilbert spaces, Banach spaces, and on sets of measures ⋮ On invariance and selectivity in representation learning ⋮ Multivariate tests of independence based on a new class of measures of independence in reproducing kernel Hilbert space ⋮ Bayesian Quadrature, Energy Minimization, and Space-Filling Design ⋮ On minimum distribution discrepancy support vector machine for domain adaptation ⋮ On the empirical estimation of integral probability metrics ⋮ Unnamed Item ⋮ Nonparametric Independence Tests: Space Partitioning and Kernel Approaches ⋮ Expected Conditional Characteristic Function-based Measures for Testing Independence ⋮ FastMMD: Ensemble of Circular Discrepancy for Efficient Two-Sample Test ⋮ Filtering with State-Observation Examples via Kernel Monte Carlo Filter ⋮ Optimal directional statistic for general regression ⋮ Krylov subspace methods for estimating operator-vector multiplications in Hilbert spaces ⋮ Unsupervised group matching with application to cross-lingual topic matching without alignment information ⋮ Remember the curse of dimensionality: the case of goodness-of-fit testing in arbitrary dimension ⋮ A kernel-based measure for conditional mean dependence ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Regularized kernel-based reconstruction in generalized Besov spaces ⋮ Kernel Distribution Embeddings: Universal Kernels, Characteristic Kernels and Kernel Metrics on Distributions ⋮ Characteristic and Universal Tensor Product Kernels ⋮ A class of optimal estimators for the covariance operator in reproducing kernel Hilbert spaces ⋮ A Kernel Multiple Change-point Algorithm via Model Selection ⋮ Equivalence of distance-based and RKHS-based statistics in hypothesis testing ⋮ Dimensionality reduction of complex metastable systems via kernel embeddings of transition manifolds ⋮ Sufficient variable selection using independence measures for continuous response ⋮ Computing functions of random variables via reproducing kernel Hilbert space representations ⋮ Equivalence of kernel machine regression and kernel distance covariance for multidimensional phenotype association studies ⋮ Continuum versus discrete networks, graph Laplacians, and reproducing kernel Hilbert spaces ⋮ Convergence analysis of deterministic kernel-based quadrature rules in misspecified settings ⋮ Unnamed Item ⋮ Eigendecompositions of transfer operators in reproducing kernel Hilbert spaces ⋮ Bayesian regression and classification using Gaussian process priors indexed by probability density functions ⋮ Discussion of: Brownian distance covariance ⋮ Global Sensitivity Analysis for Optimization with Variable Selection ⋮ Admissible kernels for RKHS embedding of probability distributions ⋮ Solving Bayesian inverse problems from the perspective of deep generative networks ⋮ Finite sample properties of parametric MMD estimation: robustness to misspecification and dependence ⋮ Robust and Scalable Bayes via a Median of Subset Posterior Measures ⋮ Minimax Estimation of Kernel Mean Embeddings ⋮ A new framework for distance and kernel-based metrics in high dimensions ⋮ Summary statistics and discrepancy measures for approximate Bayesian computation via surrogate posteriors ⋮ Model-based kernel sum rule: kernel Bayesian inference with probabilistic models ⋮ Some new copula based distribution-free tests of independence among several random variables ⋮ Graphical Models for Processing Missing Data ⋮ The basins of attraction of the global minimizers of the non-convex sparse spike estimation problem ⋮ Stabilizing Invertible Neural Networks Using Mixture Models ⋮ Unnamed Item ⋮ A Generalized Kernel Method for Global Sensitivity Analysis ⋮ Performance analysis of greedy algorithms for minimising a maximum mean discrepancy

This page was built for publication: Hilbert space embeddings and metrics on probability measures