Analysis of Langevin Monte Carlo via convex optimization

zbMATH Open1491.65009arXiv1802.09188MaRDI QIDQ5381127FDOQ5381127

Authors: Alain Durmus, Szymon Majewski, Błażej Miasojedow 

Publication date: 7 June 2019

Full work available at URL: https://arxiv.org/abs/1802.09188

Recommendations

• Higher order Langevin Monte Carlo algorithm
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Sampling from a log-concave distribution with projected Langevin Monte Carlo
• Convergence of Langevin MCMC in KL-divergence
• On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case

zbMATH Keywords

Bayesian inferenceconvex optimizationWasserstein metricgradient flowunadjusted Langevin algorithm

Mathematics Subject Classification ID

Convergence of probability measures (60B10) Monte Carlo methods (65C05) Applications of Brownian motions and diffusion theory (population genetics, absorption problems, etc.) (60J70)

Cites Work

• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Simulation-based regularized logistic regression
• Bayesian data analysis.
• Elements of Information Theory
• Exponential convergence of Langevin distributions and their discrete approximations
• Markov Chains and Stochastic Stability
• Variational Analysis
• Convex analysis and monotone operator theory in Hilbert spaces
• Introductory lectures on convex optimization. A basic course.
• Handbook of Markov Chain Monte Carlo
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
• L 1-Regularization Path Algorithm for Generalized Linear Models
• Gradient flows in metric spaces and in the space of probability measures
• Monte Carlo sampling methods using Markov chains and their applications
• Optimal Transport
• Bayesian auxiliary variable models for binary and multinomial regression
• The Bayesian elastic net
• Optimal Scaling of Discrete Approximations to Langevin Diffusions
• Equation of state calculations by fast computing machines
• A class of Wasserstein metrics for probability distributions
• Inverse problems: a Bayesian perspective
• Title not available (Why is that?)
• Title not available (Why is that?)
• Monotone Operators and the Proximal Point Algorithm
• The Variational Formulation of the Fokker--Planck Equation
• Geometry of isotropic convex bodies
• Title not available (Why is that?)
• Expansion of the global error for numerical schemes solving stochastic differential equations
• Convergence to equilibrium in Wasserstein distance for Fokker-Planck equations
• Rényi Divergence and Kullback-Leibler Divergence
• An introduction to MCMC for machine learning
• Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise.
• Statistical mechanics: Algorithms and computations. With CD-ROM.
• Existence and stability for Fokker-Planck equations with log-concave reference measure
• The Entropy Per Coordinate of a Random Vector is Highly Constrained Under Convexity Conditions
• Title not available (Why is that?)
• Title not available (Why is that?)
• RECURSIVE COMPUTATION OF THE INVARIANT DISTRIBUTION OF A DIFFUSION: THE CASE OF A WEAKLY MEAN REVERTING DRIFT
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• \{Euclidean, metric, and Wasserstein\} gradient flows: an overview
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• Optimal concentration of information content for log-concave densities
• Exploration of the (non-)asymptotic bias and variance of stochastic gradient Langevin dynamics
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
• Convergence of Langevin MCMC in KL-divergence
• Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreau

Cited In (46)

• Contraction and convergence rates for discretized kinetic Langevin dynamics
• NF-ULA: normalizing flow-based unadjusted Langevin algorithm for imaging inverse problems
• Title not available (Why is that?)
• Title not available (Why is that?)
• Optimal volume-corrected Laplace-Metropolis method
• Rapid convergence of the unadjusted Langevin algorithm: isoperimetry suffices
• Statistical inference for the population landscape via moment-adjusted stochastic gradients
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Oracle lower bounds for stochastic gradient sampling algorithms
• Constrained ensemble Langevin Monte Carlo
• From Optimization to Sampling Through Gradient Flows
• Using perturbed underdamped Langevin dynamics to efficiently sample from probability distributions
• On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case
• Kinetic Langevin MCMC sampling without gradient Lipschitz continuity -- the strongly convex case
• Convergence of Langevin MCMC in KL-divergence
• Approximate Primal-Dual Fixed-Point based Langevin Algorithms for Non-smooth Convex Potentials
• Complexity of zigzag sampling algorithm for strongly log-concave distributions
• Bayesian Stochastic Gradient Descent for Stochastic Optimization with Streaming Input Data
• Lévy Langevin Monte Carlo
• Proximal Langevin sampling with inexact proximal mapping
• Is there an analog of Nesterov acceleration for gradient-based MCMC?
• Subgradient Langevin methods for sampling from nonsmooth potentials
• Riemannian Langevin algorithm for solving semidefinite programs
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
• Optimal Monte Carlo methods for \(L^2\)-approximation
• Performance analysis of LVQ algorithms: a statistical physics approach
• Sampling can be faster than optimization
• Maximum likelihood estimation of regularization parameters in high-dimensional inverse problems: an empirical Bayesian approach. II: Theoretical analysis
• Geometric ergodicity of SGLD via reflection coupling
• Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation
• Smoothing unadjusted Langevin algorithms for nonsmooth composite potential functions
• Noise-free sampling algorithms via regularized Wasserstein proximals
• The forward-backward envelope for sampling with the overdamped Langevin algorithm
• Nonasymptotic estimates for stochastic gradient Langevin dynamics under local conditions in nonconvex optimization
• Particle dual averaging: optimization of mean field neural network with global convergence rate analysis*
• Sampling from non-smooth distributions through Langevin diffusion
• Neural-network-based regularization methods for inverse problems in imaging
• Contraction rate estimates of stochastic gradient kinetic Langevin integrators
• Appropriate state-dependent friction coefficient accelerates kinetic Langevin dynamics
• On sampling from a log-concave density using kinetic Langevin diffusions
• Laplacian smoothing stochastic gradient Markov chain Monte Carlo
• Accelerating Proximal Markov Chain Monte Carlo by Using an Explicit Stabilized Method
• Asymptotic bias of inexact Markov chain Monte Carlo methods in high dimension
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• Higher order Langevin Monte Carlo algorithm
• (Non)-penalized multilevel methods for non-uniformly log-concave distributions

Uses Software

• UCI-ml

This page was built for publication: Analysis of Langevin Monte Carlo via convex optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5381127)