Diffusion at Absolute Zero: Langevin Sampling using Successive Moreau Envelopes [journal paper]

We propose a method for sampling from Gibbs distributions of the form $\pi(x)\propto\exp(-U(x))$ by considering a family $(\pi^{t})_t$ of approximations of the target density which is such that $\pi^{t}$ exhibits favorable properties for sampling when $t$ is large, and $\pi^{t} \to \pi$ as $t \to 0$. This sequence is obtained by replacing (parts of) the potential $U$ by its Moreau envelope. Through the sequential sampling from $\pi^{t}$ for decreasing values of $t$ by a Langevin algorithm with appropriate step size, the samples are guided from a simple starting density to the more complex target quickly. We prove the ergodicity of the method as well as its convergence to the target density without assuming convexity or differentiability of the potential $U$. In addition to the theoretical analysis, we show experimental results that support the superiority of the method in terms of convergence speed and mode-coverage of multi-modal densities to current algorithms. The experiments range from one-dimensional toy-problems to high-dimensional inverse imaging problems with learned potentials.