Sampling from a log-concave distribution with projected Langevin Monte Carlo

DOI10.1007/S00454-018-9992-1zbMath1397.65010arXiv1507.02564OpenAlexW2963813262WikidataQ130021959 ScholiaQ130021959MaRDI QIDQ1650786

Joseph Lehec, Sébastien Bubeck, Ronen Eldan

Publication date: 13 July 2018

Published in: Discrete \& Computational Geometry (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1507.02564

zbMATH Keywords

log-concave measuresLangevin Monte Carlorapidly-mixing random walkssampling and optimization

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Convergence of probability measures (60B10) Applications of operator theory in optimization, convex analysis, mathematical programming, economics (47N10) Approximation algorithms (68W25) Randomized algorithms (68W20)

Related Items (24)

Oracle lower bounds for stochastic gradient sampling algorithms ⋮ Stochastic zeroth-order discretizations of Langevin diffusions for Bayesian inference ⋮ Unnamed Item ⋮ Geodesic Walks in Polytopes ⋮ Unnamed Item ⋮ On sampling from a log-concave density using kinetic Langevin diffusions ⋮ Optimising portfolio diversification and dimensionality ⋮ Ergodicity of supercritical SDEs driven by \(\alpha \)-stable processes and heavy-tailed sampling ⋮ Simplest random walk for approximating Robin boundary value problems and ergodic limits of reflected diffusions ⋮ The Langevin Monte Carlo algorithm in the non-smooth log-concave case ⋮ Efficient Bayesian Computation for Low-Photon Imaging Problems ⋮ The forward-backward envelope for sampling with the overdamped Langevin algorithm ⋮ Weak approximation of transformed stochastic gradient MCMC ⋮ Unnamed Item ⋮ User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient ⋮ Emerging directions in Bayesian computation ⋮ Stability of the Prékopa-Leindler inequality for log-concave functions ⋮ On the privacy of noisy stochastic gradient descent for convex optimization ⋮ Truncated log-concave sampling for convex bodies with reflective Hamiltonian Monte Carlo ⋮ Riemannian Langevin algorithm for solving semidefinite programs ⋮ Convergence error analysis of reflected gradient Langevin dynamics for non-convex constrained optimization ⋮ High-dimensional Bayesian inference via the unadjusted Langevin algorithm ⋮ Stochastic Gradient Markov Chain Monte Carlo ⋮ Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Representation formula for the entropy and functional inequalities
• Coupling of multidimensional diffusions by reflection
• Characterization of the law of the iterated logarithm in Banach spaces
• Stochastic differential equations with reflecting boundary condition in convex regions
• Exponential convergence of Langevin distributions and their discrete approximations
• Random Walks on Polytopes and an Affine Interior Point Method for Linear Programming
• Bypassing KLS
• The geometry of logconcave functions and sampling algorithms
• Stochastic Minimization with Constant Step-Size: Asymptotic Laws
• A random polynomial-time algorithm for approximating the volume of convex bodies
• Hit-and-Run from a Corner
• A Stochastic Approximation Method

This page was built for publication: Sampling from a log-concave distribution with projected Langevin Monte Carlo