Normalizing constants of log-concave densities

DOI10.1214/18-EJS1411zbMATH Open1473.65005arXiv1707.00460OpenAlexW2727992070WikidataQ130164309 ScholiaQ130164309MaRDI QIDQ1746544FDOQ1746544

Authors: Nicolas Brosse, Alain Durmus, Eric Moulines 

Publication date: 25 April 2018

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Abstract: We derive explicit bounds for the computation of normalizing constants $Z$ for log-concave densities $pi=exp(-U)/Z$ with respect to the Lebesgue measure on $mathbb{R}^d$. Our approach relies on a Gaussian annealing combined with recent and precise bounds on the Unadjusted Langevin Algorithm (High-dimensional Bayesian inference via the Unadjusted Langevin Algorithm, A. Durmus and E. Moulines). Polynomial bounds in the dimension $d$ are obtained with an exponent that depends on the assumptions made on $U$. The algorithm also provides a theoretically grounded choice of the annealing sequence of variances. A numerical experiment supports our findings. Results of independent interest on the mean squared error of the empirical average of locally Lipschitz functions are established.

Full work available at URL: https://arxiv.org/abs/1707.00460

Recommendations

• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• The geometry of logconcave functions and sampling algorithms
• Higher order Langevin Monte Carlo algorithm
• Sampling from a log-concave distribution with projected Langevin Monte Carlo
• Log-concave sampling: Metropolis-Hastings algorithms are fast

zbMATH Keywords

Bayes factornormalizing constantsannealed importance samplingunadjusted Langevin algorithm

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40) Sequential statistical analysis (62L10) Discrete-time Markov processes on general state spaces (60J05) (L^p)-limit theorems (60F25)

Cites Work

• Sequential Monte Carlo Samplers
• The Bayesian Choice
• Exponential convergence of Langevin distributions and their discrete approximations
• Markov chain Monte Carlo methods and the label switching problem in Bayesian mixture modeling
• Title not available (Why is that?)
• Introductory lectures on convex optimization. A basic course.
• Monte Carlo methods in Bayesian computation
• Title not available (Why is that?)
• Concentration inequalities. A nonasymptotic theory of independence
• Error bounds and normalising constants for sequential Monte Carlo samplers in high dimensions
• Optimal Transport
• Tuning tempered transitions
• Measure theory and fine properties of functions
• Simulating normalizing constants: From importance sampling to bridge sampling to path sampling
• Bayes model selection with path sampling: factor models and other examples
• Geometry of isotropic convex bodies
• Random generation of combinatorial structures from a uniform distribution
• Stability of Markovian processes III: Foster–Lyapunov criteria for continuous-time processes
• Improving power posterior estimation of statistical evidence
• Bypassing KLS: Gaussian cooling and an \(O^\ast(n^3)\) volume algorithm
• Free energy computations. A mathematical perspective
• Stochastic comparisons of order statistics from heterogeneous populations, with applications in reliability
• Fixed Precision MCMC Estimation by Median of Products of Averages
• Curvature, concentration and error estimates for Markov chain Monte Carlo
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• Title not available (Why is that?)
• Title not available (Why is that?)
• A comparative study of Monte Carlo methods for efficient evaluation of marginal likelihood
• From microphysics to macrophysics. Methods and applications of statistical physics. II. Translated from the French by D. ter Haar.
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• Multilevel Sequential Monte Carlo Samplers for Normalizing Constants
• Multilevel particle filters: normalizing constant estimation
• Normalizing constants of log-concave densities
• Approximation algorithms for the normalizing constant of Gibbs distributions
• Maximum-a-posteriori estimation with Bayesian confidence regions

Cited In (9)

• Fourier transform MCMC, heavy-tailed distributions, and geometric ergodicity
• An Invitation to Sequential Monte Carlo Samplers
• Normalizing constants of log-concave densities
• Hamiltonian Monte Carlo with energy conserving subsampling
• Multilevel estimation of normalization constants using ensemble Kalman-Bucy filters
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
• Normalizing constants of a distribution which belongs to the domain of attraction of the Gumbel distribution
• Geometry-informed irreversible perturbations for accelerated convergence of Langevin dynamics
• Unadjusted Langevin algorithm for sampling a mixture of weakly smooth potentials

Uses Software

• R

This page was built for publication: Normalizing constants of log-concave densities

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1746544)