Reproduce “Local Geometric Mixing via Dobrushin Contraction with Applications to Diffusion Path Monte Carlo and the Proximal Sampler” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Stefan Oberdörster
The authors analyze local mixing of Diffusion Path Monte Carlo and the equivalent ideal Proximal Sampler using contraction and exit probability. For any target distribution, one ideal transition reaches total-variation accuracy epsilon from starts in a bounded centered region, provided noising time is sufficiently large based on the region and target’s partial diameter. It does not extend to the Metropolis-adjusted method.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.