Projection Robust Wasserstein Distance and Riemannian Optimization

by   Tianyi Lin, et al.

Projection robust Wasserstein (PRW) distance, or Wasserstein projection pursuit (WPP), is a robust variant of the Wasserstein distance. Recent work suggests that this quantity is more robust than the standard Wasserstein distance, in particular when comparing probability measures in high-dimensions. However, it is ruled out for practical application because the optimization model is essentially non-convex and non-smooth which makes the computation intractable. Our contribution in this paper is to revisit the original motivation behind WPP/PRW, but take the hard route of showing that, despite its non-convexity and lack of nonsmoothness, and even despite some hardness results proved by <cit.> in a minimax sense, the original formulation for PRW/WPP can be efficiently computed in practice using Riemannian optimization, yielding in relevant cases better behavior than its convex relaxation. More specifically, we provide three simple algorithms with solid theoretical guarantee on their complexity bound (one in the appendix), and demonstrate their effectiveness and efficiency by conducing extensive experiments on synthetic and real data. This paper provides a first step into a computational theory of the PRW distance and provides the links between optimal transport and Riemannian optimization.



There are no comments yet.


page 1

page 2

page 3

page 4


Bures-Wasserstein Geometry

The Bures-Wasserstein distance is a Riemannian distance on the space of ...

Subspace Robust Wasserstein distances

Making sense of Wasserstein distances between discrete measures in high-...

A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance

The Wasserstein distance has become increasingly important in machine le...

Fixed-Support Wasserstein Barycenters: Computational Hardness and Fast Algorithm

We study the fixed-support Wasserstein barycenter problem (FS-WBP), whic...

Computational Hardness and Fast Algorithm for Fixed-Support Wasserstein Barycenter

We study in this paper the fixed-support Wasserstein barycenter problem ...

Projection Robust Wasserstein Barycenter

Collecting and aggregating information from several probability measures...

A First-Order Algorithmic Framework for Wasserstein Distributionally Robust Logistic Regression

Wasserstein distance-based distributionally robust optimization (DRO) ha...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.