Diffusion at Absolute Zero: Langevin Sampling Using Successive Moreau Envelopes [conference paper]
This addresses the problem of efficient sampling from multi-modal distributions for researchers in computational statistics and machine learning, representing an incremental improvement over existing methods.
The paper tackles sampling from complex Gibbs distributions by proposing a method that uses a sequence of approximations via Moreau envelopes and Annealed Langevin sampling, showing increased convergence speed and applicability to multi-modal densities in experiments.
In this article we propose a novel method for sampling from Gibbs distributions of the form $π(x)\propto\exp(-U(x))$ with a potential $U(x)$. In particular, inspired by diffusion models we propose to consider a sequence $(π^{t_k})_k$ of approximations of the target density, for which $π^{t_k}\approx π$ for $k$ small and, on the other hand, $π^{t_k}$ exhibits favorable properties for sampling for $k$ large. This sequence is obtained by replacing parts of the potential $U$ by its Moreau envelopes. Sampling is performed in an Annealed Langevin type procedure, that is, sequentially sampling from $π^{t_k}$ for decreasing $k$, effectively guiding the samples from a simple starting density to the more complex target. In addition to a theoretical analysis we show experimental results supporting the efficacy of the method in terms of increased convergence speed and applicability to multi-modal densities $π$.