Estimation of Wasserstein distances in the Spiked Transport Model

09/16/2019
by   Jonathan Niles-Weed, et al.
0

We propose a new statistical model, the spiked transport model, which formalizes the assumption that two probability distributions differ only on a low-dimensional subspace. We study the minimax rate of estimation for the Wasserstein distance under this model and show that this low-dimensional structure can be exploited to avoid the curse of dimensionality. As a byproduct of our minimax analysis, we establish a lower bound showing that, in the absence of such structure, the plug-in estimator is nearly rate-optimal for estimating the Wasserstein distance in high dimension. We also give evidence for a statistical-computational gap and conjecture that any computationally efficient estimator is bound to suffer from the curse of dimensionality.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/24/2018

Minimax Distribution Estimation in Wasserstein Distance

The Wasserstein metric is an important measure of distance between proba...
research
01/27/2019

Approximation of Wasserstein distance with Transshipment

An algorithm for approximating the p-Wasserstein distance between histog...
research
12/18/2020

Interpretable Model Summaries Using the Wasserstein Distance

In the current computing age, models can have hundreds or even thousands...
research
06/26/2022

The Sketched Wasserstein Distance for mixture distributions

The Sketched Wasserstein Distance (W^S) is a new probability distance sp...
research
02/02/2023

Robust Estimation under the Wasserstein Distance

We study the problem of robust distribution estimation under the Wassers...
research
02/02/2021

Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization

Wasserstein barycenters provide a geometric notion of the weighted avera...
research
07/24/2023

Information Geometry of Wasserstein Statistics on Shapes and Affine Deformations

Information geometry and Wasserstein geometry are two main structures in...

Please sign up or login with your details

Forgot password? Click here to reset