Minimax rates of convergence for Wasserstein deconvolution with supersmooth errors in any dimension

Abstract : The subject of this paper is the estimation of a probability measure on ${\mathbb R}^d$ from data observed with an additive noise, under the Wasserstein metric of order $p$ (with $p\geq 1$). 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 $p$. 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.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00794107
Contributor : Bertrand Michel <>
Submitted on : Monday, February 25, 2013 - 10:59:21 PM
Last modification on : Friday, September 20, 2019 - 4:34:03 PM
Long-term archiving on: Sunday, May 26, 2013 - 9:20:07 AM

Files

optimalWfinal.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00794107, version 2
  • ARXIV : 1302.6103

Citation

Jérôme Dedecker, Bertrand Michel. Minimax rates of convergence for Wasserstein deconvolution with supersmooth errors in any dimension. Journal of Multivariate Analysis, Elsevier, 2013. ⟨hal-00794107v2⟩

Share

Metrics

Record views

334

Files downloads

510