cs.DSMar 26, 2026

The Geometry of Efficient Nonconvex Sampling

Authors: Santosh S. VempalaAndre Wibisono

Organizations: Georgia Institute of Technology, College of Computing · Yale University, Department of Computer Science

Abstract

We present an efficient algorithm for uniformly sampling from an arbitrary compact body XRn\mathcal{X} \subset \mathbb{R}^n from a warm start under isoperimetry and a natural volume growth condition. Our result provides a substantial common generalization of known results for convex bodies and star-shaped bodies. The complexity of the algorithm is polynomial in the dimension, the Poincaré constant of the uniform distribution on X\mathcal{X} and the volume growth constant of the set X\mathcal{X}.

Explore similar work

CardsList