Local Geometric Mixing via Dobrushin Contraction with Applications to Diffusion Path Monte Carlo and the Proximal Sampler
math.PR, cs.LG, stat.CO, stat.ML
Submitted: 2026-09-23
Updated: 2026-09-23
Terminology
Sources
- Mirror Langevin diffusions: Convergence rates and Markov chain approximations
- High-accuracy sampling for diffusion models and log-concave distributions
- Markov Chain Monte Carlo with Diffusion Paths
- Exact Global MCMC with Denoising Diffusion
- A Proximal Algorithm for Sampling
- Alternating Diffusion for Proximal Sampling with Zeroth Order Queries
Related papers
- Sharp Deviations Bounds for Dirichlet Weighted Sums with Application to analysis of Bayesian algorithms
- Local Anticoncentration for Gaussian Boson Sampling via Conditional Wishart Geometry
- Beyond the Semicircle: Free Diffusion Models with Prescribed Equilibria
- A New Bound on the Cumulant Generating Function of Dirichlet Processes
- The Site Frequency Spectrum in an Exponentially Growing Population with Selection
- Statistical inference for a multiscale stochastic model of enzyme kinetics via propagation of chaos