Weighted quantization using MMD: From mean field to mean shift via gradient flows

arXiv:2502.10600v4 Announce Type: replace-cross Abstract: Approximating a probability distribution using a set of particles is a fundamental problem in machine learning and statistics, with applications including clustering and quantization. Formally, we seek a weighted mixture of Dirac measures that best approximates the target distribution. While much existing work relies on the Wasserstein distance to quantify approximation errors, maximum mean discrepancy (MMD) has received comparatively less attention, especially when allowing for variable particle weights. We argue that a Wasserstein-Fisher-Rao gradient flow is well-suited for designing quantizations optimal under MMD. We show that a system of interacting particles satisfying a set of ODEs discretizes this flow. We further derive a new fixed-point algorithm called mean shift interacting particles (MSIP). We show that MSIP extends the classical mean shift algorithm, widely used for identifying modes in kernel density estimators. Moreover, we show that MSIP can be interpreted as preconditioned gradient descent and that it acts as a relaxation of Lloyd's algorithm for clustering. Our unification of gradient flows, mean shift, and MMD-optimal quantization yields algorithms that are more robust than state-of-the-art methods, as demonstrated via high-dimensional and multi-modal numerical experiments.

Related

• A Scalable Nystrom-Based Kernel Two-Sample Test with Permutations
• Properties and limitations of geometric tempering for gradient flow dynamics
• UniPROT: Uniform Prototype Selection via Partial Optimal Transport with Submodular Guarantees
• Resistance Distance and Linearized Optimal Transport on Graphs
• Wasserstein-p Central Limit Theorem Rates: From Local Dependence to Markov Chains

Source: arXiv cs.LG | 2026-04-24