cs.LGNov 12, 2026

Bellman Contraction under MMD: A Unified Framework

Authors: Baptiste Debes, Tinne Tuytelaars

Organizations: ESAT-PSI, KU Leuven

Abstract

We introduce a mathematical framework for studying contraction of the distributional Bellman operator under Maximum Mean Discrepancy (MMD). We show that contraction reduces to conditional positive definiteness of an associated kernel constructed from the base kernel, which we call the Bellman difference kernel. Focusing on radial kernels, we use Schoenberg's theorem to connect this condition to Bernstein functions. This gives contraction criteria that hold in any dimension and can be verified analytically or tested numerically. Our framework unifies known results for the Gaussian RBF, power-distance, and multiquadric kernels. A numerical search identifies 11 new kernels that induce contraction. We also propose chaining, a general construction that produces kernels inducing contraction with any prescribed factor. To reconcile theory with practice, we show that contraction on a set only requires conditional positive definiteness on that set. This explains why the RBF kernel can remain a valid choice when rewards are bounded, despite its lack of global contraction. Finally, we identify a fundamental tradeoff between contraction rate and discriminative power, where kernels that contract faster tend to discriminate less between distributions. Code is available at https://github.com/BaptisteDebes/BellmanContractionMMD

Figures & tables

Appendix figures & tables24 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Kernel-based potential mean-field games with unbiased random Fourier UU-statistics

    May 28, 2026Yumiharu NakanoMulti-Agent CoordinationMean Field Games

  2. Kernel Selection is Model Selection: A Unified Complexity-Penalized Approach for MMD Two-Sample Tests

    May 7, 2026Yijin Ni, Xiaoming HuoModel SelectionTwo-Sample Testing