On the empirical estimation of integral probability metrics

DOI10.1214/12-EJS722zbMATH Open1295.62035OpenAlexW2000992741WikidataQ57340949 ScholiaQ57340949MaRDI QIDQ1950872FDOQ1950872

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

Publication date: 28 May 2013

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://projecteuclid.org/euclid.ejs/1347974672

Recommendations

• Integral Probability Metrics and Their Generating Classes of Functions
• Bounding Kolmogorov distances through Wasserstein and related integral probability metrics
• Hilbert space embeddings and metrics on probability measures
• Kernel distribution embeddings: universal kernels, characteristic kernels and kernel metrics on distributions
• A class of probability metrics and its statistical applications

zbMATH Keywords

reproducing kernel Hilbert spacesupport vector machineempirical estimationKantorovich metricDudley metricRademacher averagedual-bounded Lipschitz distanceintegral probability metricskernel distanceLipschitz classifier

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Probability measures on topological spaces (60B05)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Support-vector networks
• Probability for Statisticians
• Theory of Reproducing Kernels
• An introduction to support vector machines and other kernel-based learning methods.
• Hilbert space embeddings and metrics on probability measures
• Title not available (Why is that?)
• Learning Theory
• Support Vector Machines
• Integral Probability Metrics and Their Generating Classes of Functions
• Real Analysis and Probability
• On Choosing and Bounding Probability Metrics
• A kernel two-sample test
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• A Distribution Free Version of the Smirnov Two Sample Test in the $p$-Variate Case
• Convex Analysis
• Mass transportation problems. Vol. 1: Theory. Vol. 2: Applications
• Local Rademacher complexities
• Title not available (Why is that?)
• Title not available (Why is that?)
• Scattered Data Approximation
• Some applications of concentration inequalities to statistics
• The Monge–Kantorovich Mass Transference Problem and Its Stochastic Applications
• 10.1162/153244303321897690
• Theory of statistical inference and information. Transl. from the Slovak by the author
• Title not available (Why is that?)
• Title not available (Why is that?)
• Analytic Extensions of Differentiable Functions Defined in Closed Sets
• Extension of range of functions
• Title not available (Why is that?)
• Rademacher averages and phase transitions in Glivenko-Cantelli classes
• Refinements of Pinsker's inequality
• Title not available (Why is that?)
• Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization
• Calculation of the Wasserstein Distance Between Probability Distributions on the Line
• On surrogate loss functions and \(f\)-divergences
• A sharp concentration inequality with applications
• Divergence Estimation of Continuous Distributions Based on Data-Dependent Partitions
• Probability Metrics
• A generalization of Ornstein's \(\overline d\) distance with applications to information theory
• Title not available (Why is that?)
• Distance-based classification with Lipschitz functions
• Title not available (Why is that?)
• Title not available (Why is that?)

Cited In (39)

• A normal hierarchical model and minimum contrast estimation for random intervals
• Testing for central symmetry and inference of the unknown center
• Learning bounds of ERM principle for sequences of time-dependent samples
• Limitations of the Wasserstein MDE for univariate data
• Bounding the expectation of the supremum of empirical processes indexed by Hölder classes
• Title not available (Why is that?)
• Global Sensitivity Analysis for Optimization with Variable Selection
• Robust and parallel Bayesian model selection
• How adaptive and reliable is your program?
• On the optimal estimation of probability measures in weak and strong topologies
• Bisimulation for Markov decision processes through families of functional expressions
• Risk excess measures induced by hemi-metrics
• Kernel two-sample tests for manifold data
• Empirical optimal transport between different measures adapts to lower complexity
• Solving inverse problems in stochastic models using deep neural networks and adversarial training
• Directional differentiability for supremum-type functionals: statistical applications
• Approximation of Bayesian models for time-to-event data
• Global sensitivity analysis with dependence measures
• Principled analytic classifier for positive-unlabeled learning via weighted integral probability metric
• Stability and sample complexity of divergence regularized optimal transport
• Probabilistic model validation for uncertain nonlinear systems
• Title not available (Why is that?)
• Equivalence of distance-based and RKHS-based statistics in hypothesis testing
• An empirical evaluation of the approximation of subjective logic operators using Monte Carlo simulations
• Explicit expressions and computational methods for the Fortet-Mourier distance of positive measures to finite weighted sums of Dirac measures
• Robustness for biochemical networks: step-by-step approach
• Energy-based sequential sampling for low-rank PSD-matrix approximation
• Kernel embedding of measures and low-rank approximation of integral operators
• Model-based kernel sum rule: kernel Bayesian inference with probabilistic models
• Title not available (Why is that?)
• Geometrical Insights for Implicit Generative Modeling
• Imputation Scores
• A Generalized Kernel Method for Global Sensitivity Analysis
• Reversible Gromov-Monge sampler for simulation-based inference
• Robust and scalable Bayes via a median of subset posterior measures
• Frameworks and results in distributionally robust optimization
• A framework to measure the robustness of programs in the unpredictable environment
• Wasserstein-based fairness interpretability framework for machine learning models
• Minimax estimation of kernel mean embeddings

This page was built for publication: On the empirical estimation of integral probability metrics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1950872)