math.PRFeb 3, 2026

Functional Stochastic Localization

Authors: Anming Gu, Bobby Shi, Kevin Tian

Organizations: University of Texas at Austin

Abstract

Eldan's stochastic localization is a probabilistic construction that has proved instrumental to modern breakthroughs in high-dimensional geometry and the design of sampling algorithms. Motivated by sampling under non-Euclidean geometries and the mirror descent algorithm in optimization, we develop a functional generalization of Eldan's process that replaces Gaussian regularization with regularization by any positive integer multiple of a log-Laplace transform. We further give a mixing time bound on the Markov chain induced by our localization process, which holds if our target distribution satisfies a functional Poincaré inequality. Finally, we apply our framework to differentially private convex optimization in ℓp\ell_p norms for p∈[1,2)p \in [1, 2), where we improve state-of-the-art query complexities in a zeroth-order model.

Explore similar work

CardsList
  1. Subpolynomial-Query Proximal Sampling Beyond Log-Concavity

    Nov 2, 2026Wei Guo, Bo Yuan, Ye He +3Proximal SamplingSampling from Unnormalized Distributions