DeepAI AI Chat
Log In Sign Up

Improved analysis for a proximal algorithm for sampling

by   Yongxin Chen, et al.

We study the proximal sampler of Lee, Shen, and Tian (2021) and obtain new convergence guarantees under weaker assumptions than strong log-concavity: namely, our results hold for (1) weakly log-concave targets, and (2) targets satisfying isoperimetric assumptions which allow for non-log-concavity. We demonstrate our results by obtaining new state-of-the-art sampling guarantees for several classes of target distributions. We also strengthen the connection between the proximal sampler and the proximal method in optimization by interpreting the proximal sampler as an entropically regularized Wasserstein proximal method, and the proximal point method as the limit of the proximal sampler with vanishing noise.


Improved dimension dependence of a proximal algorithm for sampling

We propose a sampling algorithm that achieves superior complexity bounds...

Faster high-accuracy log-concave sampling via algorithmic warm starts

Understanding the complexity of sampling from a strongly log-concave and...

Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler

The development of efficient sampling algorithms catering to non-Euclide...

Skew Brownian Motion and Complexity of the ALPS Algorithm

Simulated tempering is a popular method of allowing MCMC algorithms to m...

Structured Logconcave Sampling with a Restricted Gaussian Oracle

We give algorithms for sampling several structured logconcave families t...

Proximal Langevin Algorithm: Rapid Convergence Under Isoperimetry

We study the Proximal Langevin Algorithm (PLA) for sampling from a proba...

Multi-segment preserving sampling for deep manifold sampler

Deep generative modeling for biological sequences presents a unique chal...