The forward-backward envelope for sampling with the overdamped Langevin algorithm

DOI10.1007/s11222-023-10254-yzbMath1516.62012arXiv2201.09096OpenAlexW4378905084MaRDI QIDQ6173566

No author found.

Publication date: 21 July 2023

Published in: Statistics and Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2201.09096

zbMATH Keywords

convex optimizationMarkov chain Monte CarloLangevin equation

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Convex programming (90C25)

Related Items (1)

Smoothing unadjusted Langevin algorithms for nonsmooth composite potential functions

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Nonlinear total variation based noise removal algorithms
• Smooth minimization of non-smooth functions
• On weighted parallel volumes
• Computing ergodic limits for Langevin equations
• Exponential convergence of Langevin distributions and their discrete approximations
• An algorithm for total variation minimization and applications
• Sampling from a log-concave distribution with projected Langevin Monte Carlo
• Sampling from non-smooth distributions through Langevin diffusion
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• Forward-backward quasi-Newton methods for nonsmooth optimization problems
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Proximal Markov chain Monte Carlo algorithms
• Quantitative contraction rates for Markov chains on general state spaces
• Coupling and convergence for Hamiltonian Monte Carlo
• Nonasymptotic bounds for sampling algorithms without log-concavity
• High Order Numerical Approximation of the Invariant Measure of Ergodic SDEs
• Convergence of Numerical Time-Averaging and Stationary Measures via Poisson Equations
• Handbook of Markov Chain Monte Carlo
• First-Order Methods in Optimization
• Efficient Bayesian Computation by Proximal Markov Chain Monte Carlo: When Langevin Meets Moreau
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• Optimal Transport

This page was built for publication: The forward-backward envelope for sampling with the overdamped Langevin algorithm