Proximal Algorithms for Accelerated Langevin Dynamics

Duy H. Thai, Alexander L. Young, David B. Dunson
11/24/2023
cs.CEcs.CV

No confident code implementation found for this paper.

Abstract

We develop a novel class of MCMC algorithms based on a stochastized Nesterov scheme. With an appropriate addition of noise, the result is a time-inhomogeneous underdamped Langevin equation, which we prove emits a specified target distribution as its invariant measure. Convergence rates to stationarity under Wasserstein-2 distance are established as well. Metropolis-adjusted and stochastic gradient versions of the proposed Langevin dynamics are also provided. Experimental illustrations show superior performance of the proposed method over typical Langevin samplers for different models in statistics and image processing including better mixing of the resulting Markov chains.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

79% match1 repo9002017

Stochastic Approximation with Decision-Dependent Distributions: Asymptotic Normality and Optimality

79% match2022

A Gradient Smoothed Functional Algorithm with Truncated Cauchy Random Perturbations for Stochastic Optimization

78% match2022

Second Order Ensemble Langevin Method for Sampling and Inverse Problems

78% match2022

Langevin Quasi-Monte Carlo

77% match2026

Neural Kolmogorov Equations: Parallelizable Learning of Stochastic Dynamics under General Noise

77% match2026

Cite this paper

@article{thai2023proximal,
  title  = {Proximal Algorithms for Accelerated Langevin Dynamics},
  author = {Duy H. Thai and Alexander L. Young and David B. Dunson},
  year   = {2023},
  eprint = {2311.14829},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.14829v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.14829.svg)](https://codeofpaper.com/paper/2311.14829)

Discussion