Proximal Langevin Algorithm: Rapid Convergence Under Isoperimetry

Abstract

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 Rényi divergence of order $q>1$ when the biased limit satisfies either LSI or Poincaré inequality.

References in corpus (16)

• Deep Learning with Differential Privacy
• Rényi Divergence and Kullback-Leibler Divergence
• Renyi Differential Privacy
• Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm
• Convergence of Langevin MCMC in KL-divergence
• Uncertainty quantification for radio interferometric imaging: I. proximal MCMC methods
• Rapid Mixing of Hamiltonian Monte Carlo on Strongly Log-Concave Distributions
• Uncertainty quantification for radio interferometric imaging: II. MAP estimation
• Is There an Analog of Nesterov Acceleration for MCMC?
• Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Suffices
• Dimensionally Tight Bounds for Second-Order Hamiltonian Monte Carlo
• Preconditioned P-ULA for Joint Deconvolution-Segmentation of Ultrasound Images -- Extended Version
• Exponential decay of Rényi divergence under Fokker-Planck equations
• An Efficient Sampling Algorithm for Non-smooth Composite Potentials
• Accelerating proximal Markov chain Monte Carlo by using an explicit stabilised method
• Implicit Langevin Algorithms for Sampling From Log-concave Densities

Cited by in corpus (9)

• Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm
• Information Newton's flow: second-order optimization method in probability space
• Efficient constrained sampling via the mirror-Langevin algorithm
• Composite Logconcave Sampling with a Restricted Gaussian Oracle
• Structured Logconcave Sampling with a Restricted Gaussian Oracle
• The Wasserstein Proximal Gradient Algorithm
• Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization
• Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev
• The query complexity of sampling from strongly log-concave distributions in one dimension