On the empirical estimation of integral probability metrics

DOI10.1214/12-EJS722zbMath1295.62035OpenAlexW2000992741WikidataQ57340949 ScholiaQ57340949MaRDI QIDQ1950872

Kenji Fukumizu, Bharath K. Sriperumbudur, 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

zbMATH Keywords

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

Mathematics Subject Classification ID

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

Related Items

On the optimal estimation of probability measures in weak and strong topologies, Frameworks and results in distributionally robust optimization, Testing for central symmetry and inference of the unknown center, Robust and parallel Bayesian model selection, Directional differentiability for supremum-type functionals: statistical applications, Principled analytic classifier for positive-unlabeled learning via weighted integral probability metric, Explicit expressions and computational methods for the Fortet-Mourier distance of positive measures to finite weighted sums of Dirac measures, A framework to measure the robustness of programs in the unpredictable environment, Geometrical Insights for Implicit Generative Modeling, Approximation of Bayesian models for time-to-event data, Probabilistic model validation for uncertain nonlinear systems, Learning bounds of ERM principle for sequences of time-dependent samples, Solving inverse problems in stochastic models using deep neural networks and adversarial training, Bounding the expectation of the supremum of empirical processes indexed by Hölder classes, Unnamed Item, Unnamed Item, Unnamed Item, Bisimulation for Markov Decision Processes through Families of Functional Expressions, Equivalence of distance-based and RKHS-based statistics in hypothesis testing, Imputation Scores, An empirical evaluation of the approximation of subjective logic operators using Monte Carlo simulations, Risk excess measures induced by hemi-metrics, Global sensitivity analysis with dependence measures, Global Sensitivity Analysis for Optimization with Variable Selection, Robust and Scalable Bayes via a Median of Subset Posterior Measures, Minimax Estimation of Kernel Mean Embeddings, Model-based kernel sum rule: kernel Bayesian inference with probabilistic models, Wasserstein-based fairness interpretability framework for machine learning models, A Generalized Kernel Method for Global Sensitivity Analysis, Limitations of the Wasserstein MDE for univariate data, A normal hierarchical model and minimum contrast estimation for random intervals, How adaptive and reliable is your program?

Cites Work

• On surrogate loss functions and \(f\)-divergences
• Theory of statistical inference and information. Transl. from the Slovak by the author
• A generalization of Ornstein's \(\overline d\) distance with applications to information theory
• Mass transportation problems. Vol. 1: Theory. Vol. 2: Applications
• Support-vector networks
• Weak convergence and empirical processes. With applications to statistics
• Local Rademacher complexities
• Hilbert space embeddings and metrics on probability measures
• Probability Metrics
• Learning Theory
• Support Vector Machines
• Divergence Estimation of Continuous Distributions Based on Data-Dependent Partitions
• The Monge–Kantorovich Mass Transference Problem and Its Stochastic Applications
• Calculation of the Wasserstein Distance Between Probability Distributions on the Line
• Integral Probability Metrics and Their Generating Classes of Functions
• A sharp concentration inequality with applications
• Probability for Statisticians
• Rademacher averages and phase transitions in Glivenko-Cantelli classes
• Refinements of Pinsker's inequality
• Analytic Extensions of Differentiable Functions Defined in Closed Sets
• Extension of range of functions
• Real Analysis and Probability
• 10.1162/153244303321897690
• On Choosing and Bounding Probability Metrics
• Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization
• A Distribution Free Version of the Smirnov Two Sample Test in the $p$-Variate Case
• Convex Analysis
• Theory of Reproducing Kernels
• Scattered Data Approximation
• Some applications of concentration inequalities to statistics
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item