Gromov-Wasserstein Quantization and Clustering: Structure, Rates, and Algorithms

2026-08-11

AI Summary

This work addresses a key limitation of traditional clustering methods—such as k-means—which operate solely within a fixed metric space and cannot simultaneously learn the underlying geometric structure of the data. To overcome this, the paper introduces the Gromov–Wasserstein (GW) distance into a quantization and clustering framework, proposing a Lloyd-type iterative algorithm that jointly models both the data points and their intrinsic geometry. Theoretically, the study establishes the existence of GW-optimal quantizers and derives their convergence rates. Empirically, the method demonstrates strong performance on tasks including 3D shape clustering based on geodesic distances and structured pruning of neural networks, achieving quantization rates that closely approach the theoretically optimal bounds.

Abstract

Clustering is a fundamental class of data analysis techniques with the most important representatives being centroid-based methods like $k$-means. Such methods are strongly connected to quantization problems, which aim to approximate general probability measures with discrete ones. For example, $k$-means corresponds to quantization with respect to the Wasserstein distance. While Wasserstein quantization clusters points within a fixed space, this paper studies Gromov-Wasserstein (GW) quantization, which additionally aims at clustering the ambient geometry of the space. We show existence of solutions to the GW quantization problem and give a characterization that justifies an analogue to the $k$-means algorithm (Lloyd's algorithm) to approximate them numerically. We further calculate the quantization rate for usual Euclidean geometries that are used in the GW context, and relate it to standard Wasserstein quantization rates. Finally, numerical experiments show that GW quantization opens up many modeling possibilities beyond normal clustering methods (e.g., for geodesic distances of 3D shapes or structured pruning of neural networks) and that the introduced algorithm leads to useful numerical solutions with approximation quality often in line with theoretically optimal rates.

Problem

• Gromov-Wasserstein quantization
• clustering
• geometry
• Wasserstein distance
• quantization

Innovation

• Gromov-Wasserstein quantization
• geometric clustering
• quantization rates
• Lloyd-type algorithm
• structured data analysis