Empirical measures: regularity is a counter-curse to dimensionality
From MaRDI portal
(Redirected from Publication:5135952)
Abstract: We propose a "decomposition method" to prove non-asymptotic bound for the convergence of empirical measures in various dual norms. The main point is to show that if one measures convergence in duality with sufficiently regular observables, the convergence is much faster than for, say, merely Lipschitz observables. Actually, assuming derivatives with ( the dimension) ensures an optimal rate of convergence of ( the number of samples). The method is flexible enough to apply to Markov chains which satisfy a geometric contraction hypothesis, assuming neither stationarity nor reversibility, with the same convergence speed up to a power of logarithm factor. Our results are stated as controls of the expected distance between the empirical measure and its limit, but we explain briefly how the classical method of bounded difference can be used to deduce concentration estimates.
Recommendations
- On the mean speed of convergence of empirical and occupation measures in Wasserstein distance
- On the rate of convergence in Wasserstein distance of the empirical measure
- Quantitative concentration inequalities for empirical measures on non-compact spaces
- Convergence rates for empirical measures of Markov chains in dual and Wasserstein distances
- On the Rate of Convergence of Empirical Measures in ∞-transportation Distance
Cites work
- L^\infty -Multivariate Approximation Theory
- A new Poisson-type deviation inequality for Markov jump processes with positive Wasserstein curvature
- A PDE approach to a 2-dimensional matching problem
- An optimal transportation approach to the decay of correlations for non-uniformly expanding maps
- Behavior of the empirical Wasserstein distance in \({\mathbb R}^d\) under moment conditions
- Concentration inequalities for Markov processes via coupling
- Constructive quantization: approximation by empirical measures
- Contraction in the Wasserstein metric for some Markov chains, and applications to the dynamics of expanding maps
- Curvature, concentration and error estimates for Markov chain Monte Carlo
- Deviation inequalities for separately Lipschitz functionals of iterated random functions
- Effective Berry-Esseen and concentration bounds for Markov chains with a spectral gap
- scientific article; zbMATH DE number 412139 (Why is no real title available?)
- scientific article; zbMATH DE number 3964277 (Why is no real title available?)
- Matching random samples in many dimensions
- Mixing and concentration by Ricci curvature
- Near-best multivariate approximation by Fourier series, Chebyshev series and Chebyshev interpolation
- Obtaining measure concentration from Markov contraction
- On \(\mathcal{H}^1\) and entropic convergence for contractive PDMP
- On optimal matchings
- On the mean speed of convergence of empirical and occupation measures in Wasserstein distance
- On the rate of convergence in Wasserstein distance of the empirical measure
- Optimal concentration inequalities for dynamical systems
- Orthonormal bases of compactly supported wavelets
- Reflection couplings and contraction rates for diffusions
- Ricci curvature of Markov chains on metric spaces
- Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
- Sharper bounds for Gaussian and empirical processes
Cited in
(13)- Behavior of the empirical Wasserstein distance in \({\mathbb R}^d\) under moment conditions
- Minimax estimation of smooth densities in Wasserstein distance
- Convergence rates for empirical measures of Markov chains in dual and Wasserstein distances
- Risk bounds when learning infinitely many response functions by ordinary linear regression
- Optimal transportation and stationary measures for iterated function systems
- A class of dimension-free metrics for the convergence of empirical measures
- Stability and sample complexity of divergence regularized optimal transport
- On concentration of the empirical measure for radial transport costs
- Learning conditional distributions on continuous spaces
- Empirical approximation to invariant measures of non-degenerate McKean-Vlasov dynamics
- Convergence of empirical optimal transport in unbounded settings
- Asymptotic quantization of measures on Riemannian manifolds via covering growth estimates
- Efficient random walks on Riemannian manifolds
This page was built for publication: Empirical measures: regularity is a counter-curse to dimensionality
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5135952)
