In-and-Out: Algorithmic Diffusion for Sampling Convex Bodies

arXiv:2405.01425v1 Announce Type: cross
Abstract: We present a new random walk for uniformly sampling high-dimensional convex bodies. It achieves state-of-the-art runtime complexity with stronger guarantees on the output than previously known, namely in R\'enyi divergence (which implies TV, $\mathcal{W}_2$, KL, $\chi^2$). The proof departs from known approaches for polytime algorithms for the problem -- we utilize a stochastic diffusion perspective to show contraction to the target distribution with the rate of convergence determined by functional isoperimetric constants of the stationary …

abstract algorithms art arxiv complexity cs.ds cs.lg diffusion divergence math.st random sampling state stat.ml stat.th type