DeepAI
Log In Sign Up

A Simple Duality Proof for Wasserstein Distributionally Robust Optimization

04/30/2022
by   Luhao Zhang, et al.
0

We present a short and elementary proof of the duality for Wasserstein distributionally robust optimization, which holds for any arbitrary Kantorovich transport distance, any arbitrary measurable loss function, and any arbitrary nominal probability distribution, as long as certain interchangeability principle holds.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/02/2021

Outlier-Robust Optimal Transport: Duality, Structure, and Statistical Analysis

The Wasserstein distance, rooted in optimal transport (OT) theory, is a ...
01/20/2021

A short proof on the rate of convergence of the empirical measure for the Wasserstein distance

We provide a short proof that the Wasserstein distance between the empir...
12/07/2020

Sobolev Wasserstein GAN

Wasserstein GANs (WGANs), built upon the Kantorovich-Rubinstein (KR) dua...
09/08/2019

Distributionally Robust Optimization with Correlated Data from Vector Autoregressive Processes

We present a distributionally robust formulation of a stochastic optimiz...
09/03/2022

Entropy-regularized Wasserstein distributionally robust shape and topology optimization

This brief note aims to introduce the recent paradigm of distributional ...
06/12/2020

Projection Robust Wasserstein Distance and Riemannian Optimization

Projection robust Wasserstein (PRW) distance, or Wasserstein projection ...
03/08/2018

Distributed Computation of Wasserstein Barycenters over Networks

We propose a new class-optimal algorithm for the distributed computation...