AI RESEARCH
In-and-Out: Algorithmic Diffusion for Sampling Convex Bodies
arXiv CS.LG
•
ArXi:2405.01425v4 Announce Type: replace-cross 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