paper-with-me

Papers

Proximal Langevin Algorithm: Rapid Convergence Under Isoperimetry

2019-11-04 · Andre Wibisono

We study the Proximal Langevin Algorithm (PLA) for sampling from a probability distribution $\nu = e^{-f}$ on $\mathbb{R}^n$ under isoperimetry. We prove a convergence guarantee for PLA in Kullback-Leibler (KL) divergence when $\nu$ satisfies log-Sobolev inequality (LSI) and $f$ has bounded second and third derivatives. This improves on the result for the Unadjusted Langevin Algorithm (ULA), and matches the fastest known rate for sampling under LSI (without Metropolis filter) with a better dependence on the LSI constant. We also prove convergence guarantees for PLA in R\'enyi divergence of order $q > 1$ when the biased limit satisfies either LSI or Poincar\'e inequality.

📄 PDF Abstract BibTeX arXiv:1911.01469

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling

2025-05-20 · Marien Renaud, Valentin De Bortoli, Arthur Leclaire, Nicolas Papadakis

We consider the problem of sampling distributions stemming from non-convex potentials with Unadjusted Langevin Algorithm (ULA). We prove the stability of the discrete-time ULA to drift approximations under the assumption…

Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates

2019-05-28 · NeurIPS 2019 12 · Adil Salim, Dmitry Kovalev, Peter Richtárik

We propose a new algorithm---Stochastic Proximal Langevin Algorithm (SPLA)---for sampling from a log concave distribution. Our method is a generalization of the Langevin algorithm to potentials expressed as the sum of on…

Faster Sampling via Stochastic Gradient Proximal Sampler

2024-05-27 · Xunpeng Huang, Difan Zou, Yi-An Ma, Hanze Dong 외

Stochastic gradients have been widely integrated into Langevin-based methods to improve their scalability and efficiency in solving large-scale sampling problems. However, the proximal sampler, which exhibits much faster…

Mixing Time of the Proximal Sampler in Relative Fisher Information via Strong Data Processing Inequality

2025-02-08 · Andre Wibisono

We study the mixing time guarantee for sampling in relative Fisher information via the Proximal Sampler algorithm, which is an approximate proximal discretization of the Langevin dynamics. We show that when the target pr…

Proximal Algorithms for Accelerated Langevin Dynamics

2023-11-24 · Duy H. Thai, Alexander L. Young, David B. Dunson

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 specifi…