AI Chat

Minimax Distribution Estimation in Wasserstein Distance

02/24/2018

∙

by Shashank Singh, et al.

∙

Carnegie Mellon University

∙

∙

The Wasserstein metric is an important measure of distance between probability distributions, with several applications in machine learning, statistics, probability theory, and data analysis. In this paper, we upper and lower bound minimax rates for the problem of estimating a probability distribution under Wasserstein loss, in terms of metric properties, such as covering and packing numbers, of the underlying sample space.

Shashank Singh
20 publications
Barnabas Poczos
101 publications

page 1

page 2

page 3

page 4

∙ 08/27/2019

On the Minimax Optimality of Estimating the Wasserstein Metric

We study the minimax optimal rate for estimating the Wasserstein-1 metri...

0 Tengyuan Liang, et al. ∙

∙ 09/17/2019

Minimax Confidence Intervals for the Sliced Wasserstein Distance

The Wasserstein distance has risen in popularity in the statistics and m...

4 Tudor Manole, et al. ∙

∙ 06/26/2022

The Sketched Wasserstein Distance for mixture distributions

The Sketched Wasserstein Distance (W^S) is a new probability distance sp...

0 Xin Bing, et al. ∙

∙ 09/16/2019

Estimation of Wasserstein distances in the Spiked Transport Model

We propose a new statistical model, the spiked transport model, which fo...

0 Jonathan Niles-Weed, et al. ∙

∙ 02/12/2018

A note on reinforcement learning with Wasserstein distance regularisation, with applications to multipolicy learning

In this note we describe an application of Wasserstein distance to Reinf...

0 Mohammed Amin Abdullah, et al. ∙

∙ 09/09/2020

The Unbalanced Gromov Wasserstein Distance: Conic Formulation and Relaxation

Comparing metric measure spaces (i.e. a metric space endowed with a prob...

5 Thibault Séjourné, et al. ∙

∙ 09/14/2022

Wasserstein K-means for clustering probability distributions

Clustering is an important exploratory data analysis technique to group ...

0 Yubo Zhuang, et al. ∙