English

The Geometry of Efficient Nonconvex Sampling

Data Structures and Algorithms 2026-03-27 v1 Machine Learning Statistics Theory Machine Learning Statistics Theory

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 Poincar\'e constant of the uniform distribution on X\mathcal{X} and the volume growth constant of the set X\mathcal{X}.

Keywords

Cite

@article{arxiv.2603.25622,
  title  = {The Geometry of Efficient Nonconvex Sampling},
  author = {Santosh S. Vempala and Andre Wibisono},
  journal= {arXiv preprint arXiv:2603.25622},
  year   = {2026}
}
R2 v1 2026-07-01T11:39:31.375Z