Article Dans Une Revue ESAIM: Probability and Statistics Année : 2020

Empirical measures: regularity is a counter-curse to dimensionality

Résumé

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 s derivatives with s > d∕2 (d the dimension) ensures an optimal rate of convergence of 1/√n (n 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.

Fichier principal
Vignette du fichier
ps180061.pdf (536.98 Ko) Télécharger le fichier
Origine Publication financée par une institution
Licence
Loading...
HAL

A pour origine hal-02949705 Article Benoît R. Kloeckner. Empirical measures: regularity is a counter-curse to dimensionality. ESAIM: Probability and Statistics, 2020, 24, pp.408-434. ⟨10.1051/ps/2019025⟩. ⟨hal-02949705v2⟩

Dates et versions

hal-02949705 , version 1 (11-02-2018)
hal-02949705 , version 2 (25-09-2020)

Licence

Identifiants

Citer

Benoît R. Kloeckner. Empirical measures: regularity is a counter-curse to dimensionality. ESAIM: Probability and Statistics, 2020, 24, pp.408-434. ⟨10.1051/ps/2019025⟩. ⟨hal-02949705v2⟩
154 Consultations
430 Téléchargements

Altmetric

Partager

  • More