Improved rates for Wasserstein deconvolution with ordinary smooth error in dimension one

Abstract : This paper deals with the estimation of a probability measure on the real line from data observed with an additive noise. We are interested in rates of convergence for the Wasserstein metric of order $p\geq 1$. The distribution of the errors is assumed to be known and to belong to a class of supersmooth or ordinary smooth distributions. We obtain in the univariate situation an improved upper bound in the ordinary smooth case and less restrictive conditions for the existing bound in the supersmooth one. In the ordinary smooth case, a lower bound is also provided, and numerical experiments illustrating the rates of convergence are presented.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.sorbonne-universite.fr/hal-00971316
Contributor : Bertrand Michel <>
Submitted on : Tuesday, March 3, 2015 - 10:00:18 PM
Last modification on : Friday, September 20, 2019 - 4:34:03 PM
Long-term archiving on : Saturday, September 12, 2015 - 10:25:18 PM

Files

WassersteinRev1.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00971316, version 2
  • ARXIV : 1404.0646

Collections

Citation

Jérôme Dedecker, Aurélie Fischer, Bertrand Michel. Improved rates for Wasserstein deconvolution with ordinary smooth error in dimension one. 2014. ⟨hal-00971316v2⟩

Share

Metrics

Record views

268

Files downloads

156