Approximating the Optimal Transport Plan via Particle-Evolving Method

TL;DR

This paper introduces a novel particle-evolving algorithm to approximate the optimal transport plan between continuous probability measures, addressing computational challenges in Wasserstein distance calculations.

Contribution

It presents a new iterative particle-based method derived from gradient flow of an Entropy Transport Problem, with theoretical and empirical validation.

Findings

Algorithm effectively approximates optimal transport plans.

Theoretical analysis supports convergence and stability.

Empirical results demonstrate practical efficiency.

Abstract

Optimal transport (OT) provides powerful tools for comparing probability measures in various types. The Wasserstein distance which arises naturally from the idea of OT is widely used in many machine learning applications. Unfortunately, computing the Wasserstein distance between two continuous probability measures always suffers from heavy computational intractability. In this paper, we propose an innovative algorithm that iteratively evolves a particle system to match the optimal transport plan for two given continuous probability measures. The derivation of the algorithm is based on the construction of the gradient flow of an Entropy Transport Problem which could be naturally understood as a classical Wasserstein optimal transport problem with relaxed marginal constraints. The algorithm comes with theoretical analysis and empirical evidence.