DeepAI AI Chat
Log In Sign Up

Theoretical guarantees for approximate sampling from smooth and log-concave densities

by   Arnak S. Dalalyan, et al.
Ensae ParisTech

Sampling from various kinds of distributions is an issue of paramount importance in statistics since it is often the key ingredient for constructing estimators, test procedures or confidence intervals. In many situations, the exact sampling from a given distribution is impossible or computationally expensive and, therefore, one needs to resort to approximate sampling strategies. However, there is no well-developed theory providing meaningful nonasymptotic guarantees for the approximate sampling procedures, especially in the high-dimensional problems. This paper makes some progress in this direction by considering the problem of sampling from a distribution having a smooth and log-concave density defined on ^p, for some integer p>0. We establish nonasymptotic bounds for the error of approximating the target distribution by the one obtained by the Langevin Monte Carlo method and its variants. We illustrate the effectiveness of the established guarantees with various experiments. Underlying our analysis are insights from the theory of continuous-time diffusion processes, which may be of interest beyond the framework of log-concave densities considered in the present work.


page 1

page 2

page 3

page 4


Non-Asymptotic Guarantees For Sampling by Stochastic Gradient Descent

Sampling from various kinds of distributions is an issue of paramount im...

On sampling from a log-concave density using kinetic Langevin diffusions

Langevin diffusion processes and their discretizations are often used fo...

Towards a Theory of Non-Log-Concave Sampling: First-Order Stationarity Guarantees for Langevin Monte Carlo

For the task of sampling from a density π∝exp(-V) on ℝ^d, where V is pos...

Spectral Gap of Replica Exchange Langevin Diffusion on Mixture Distributions

Langevin diffusion (LD) is one of the main workhorses for sampling probl...

Conditionally Strongly Log-Concave Generative Models

There is a growing gap between the impressive results of deep image gene...

Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited

We revisit the problem of sampling from a target distribution that has a...