Efficient robust optimal transport: formulations and algorithms

10/22/2020
by   Pratik Jawanpuria, et al.
0

The problem of robust optimal transport (OT) aims at recovering the best transport plan with respect to the worst possible cost function. In this work, we study novel robust OT formulations where the cost function is parameterized by a symmetric positive semi-definite Mahalanobis metric. In particular, we study several different regularizations on the Mahalanobis metric – element-wise p-norm, KL-divergence, or doubly-stochastic constraint – and show that the resulting optimization formulations can be considerably simplified by exploiting the problem structure. For large-scale applications, we additionally propose a suitable low-dimensional decomposition of the Mahalanobis metric for the studied robust OT problems. Overall, we view the robust OT (min-max) optimization problems as non-linear OT (minimization) problems, which we solve using a Frank-Wolfe algorithm. We discuss the use of robust OT distance as a loss function in multi-class/multi-label classification problems. Empirical results on several real-world tag prediction and multi-class datasets show the benefit of our modeling approach.

READ FULL TEXT

page 9

page 10

research
03/07/2023

New Perspectives on Regularization and Computation in Optimal Transport-Based Distributionally Robust Optimization

We study optimal transport-based distributionally robust optimization pr...
research
11/10/2020

Unbalanced Optimal Transport using Integral Probability Metric Regularization

Unbalanced Optimal Transport (UOT) is the generalization of classical op...
research
08/04/2021

Statistical Analysis of Wasserstein Distributionally Robust Estimators

We consider statistical methods which invoke a min-max distributionally ...
research
08/04/2019

Pairwise Multi-marginal Optimal Transport via Universal Poisson Coupling

We investigate the problem of pairwise multi-marginal optimal transport,...
research
06/15/2020

COT-GAN: Generating Sequential Data via Causal Optimal Transport

We introduce COT-GAN, an adversarial algorithm to train implicit generat...
research
11/08/2022

Scalable multi-class sampling via filtered sliced optimal transport

We propose a multi-class point optimization formulation based on continu...
research
02/17/2019

Metric properties of homogeneous and spatially inhomogeneous F-divergences

In this paper I investigate the construction and the properties of the s...

Please sign up or login with your details

Forgot password? Click here to reset