Minimax rates of convergence for Wasserstein deconvolution with supersmooth errors in any dimension
From MaRDI portal
(Redirected from Publication:391892)
Abstract: The subject of this paper is the estimation of a probability measure on from data observed with an additive noise, under the Wasserstein metric of order (with ). We assume that the distribution of the errors is known and belongs to a class of supersmooth distributions, and we give optimal rates of convergence for the Wasserstein metric of order . In particular, we show how to use the existing lower bounds for the estimation of the cumulative distribution function in dimension one to find lower bounds for the Wasserstein deconvolution in any dimension.
Recommendations
- Improved rates for Wasserstein deconvolution with ordinary smooth error in dimension one
- Deconvolution with supersmooth distributions
- Deconvolution for the Wasserstein metric and geometric inference
- Bayes and maximum likelihood for \(L^1\)-Wasserstein deconvolution of Laplace mixtures
- Deconvolution of supersmooth densities with smooth noise
Cites work
- Adaptively local one-dimensional subproblems with application to a deconvolution problem
- Anisotropic adaptive kernel deconvolution
- Deconvolution for the Wasserstein metric and geometric inference
- Deconvolution problems in nonparametric statistics
- Deconvolution with supersmooth distributions
- Geometric inference for probability measures
- scientific article; zbMATH DE number 775754 (Why is no real title available?)
- Introduction to nonparametric estimation
- Manifold estimation and singular deconvolution under Hausdorff loss
- Mass transportation problems. Vol. 1: Theory. Vol. 2: Applications
- Nonparametric regression with errors in variables
- On deconvolution of distribution functions
- On the optimal rates of convergence for nonparametric deconvolution problems
- Optimal Rates of Convergence for Deconvolving a Density
- Sharp Optimality in Density Deconvolution with Dominating Bias. I
- Sharp Optimality in Density Deconvolution with Dominating Bias. II
- Stability of a 4th-order curvature condition arising in optimal transport theory
Cited in
(18)- Bayes and maximum likelihood for \(L^1\)-Wasserstein deconvolution of Laplace mixtures
- Sharp minimaxity and spherical deconvolution for super-smooth error distributions
- Deconvolution for the Wasserstein metric and geometric inference
- Strong identifiability and optimal minimax rates for finite mixture estimation
- Minimax estimation of smooth optimal transport maps
- Minimax estimation of smooth densities in Wasserstein distance
- Uniform convergence rates for wavelet curve estimation in sup-norm loss
- Improved rates for Wasserstein deconvolution with ordinary smooth error in dimension one
- On minimax convergence rates under \(L^p\)-risk for the anisotropic functional deconvolution model
- Deconvolution for the Wasserstein metric and geometric inference
- Deconvolution for some singular density errors via a combinatorial median of means approach
- Wasserstein convergence in Bayesian and frequentist deconvolution models
- Minimax rates for Wasserstein deconvolution of regular distributions with known ordinary smooth errors
- Adaptive minimax-optimal Wasserstein deconvolution with unknown error distributions
- Multivariate, heteroscedastic empirical Bayes via nonparametric maximum likelihood
- Minimax rates for Wasserstein deconvolution of regular distributions with ordinary smooth errors
- Minimax optimal rates of convergence in monotone shuffled and unlinked regression models under vanishing noise
- Adaptive Bayesian density estimation in \(L^p\)-metrics with Pitman-Yor or normalized inverse-Gaussian process kernel mixtures
This page was built for publication: Minimax rates of convergence for Wasserstein deconvolution with supersmooth errors in any dimension
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q391892)
