Transport Clustering: Solving Low-Rank Optimal Transport via Clustering

TL;DR

This paper introduces transport clustering, an efficient algorithm for low-rank optimal transport that reduces the problem to clustering, providing approximation guarantees and outperforming existing methods on benchmarks.

Contribution

It presents a polynomial-time approximation algorithm for low-rank OT by reducing it to a clustering problem, with theoretical guarantees and empirical improvements.

Findings

Outperforms existing low-rank OT solvers on benchmarks

Provides polynomial-time approximation algorithms with provable guarantees

Achieves better statistical stability and robustness in OT estimation

Abstract

Optimal transport (OT) finds a least cost transport plan between two probability distributions using a cost matrix defined on pairs of points. Unlike standard OT, which infers unstructured pointwise mappings, low-rank optimal transport explicitly constrains the rank of the transport plan to infer latent structure. This improves statistical stability and robustness, yields sharper parametric rates for estimating Wasserstein distances adaptive to the intrinsic rank, and generalizes $K$-means to co-clustering. These advantages, however, come at the cost of a non-convex and NP-hard optimization problem. We introduce transport clustering, an algorithm to compute a low-rank OT plan that reduces low-rank OT to a clustering problem on correspondences obtained from a full-rank $\textit{transport registration}$ step. We prove that this reduction yields polynomial-time, constant-factor approximation algorithms for low-rank OT: specifically, a $(1+\gamma)$ approximation for negative-type metrics and a $(1+\gamma+\sqrt{2\gamma}\,)$ approximation for kernel costs, where $\gamma \in [0,1]$ denotes the approximation ratio of the optimal full-rank solution relative to the low-rank optimal. Empirically, transport clustering outperforms existing low-rank OT solvers on synthetic benchmarks and large-scale, high-dimensional datasets.