Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

High-dimensional Bayesian inference via the Unadjusted Langevin Algorithm

Abstract : We consider in this paper the problem of sampling a high-dimensional probability distribution $\pi$ having a density wrt the Lebesgue measure on $\mathbb{R}^d$, known up to a normalisation factor $x \mapsto \mathrm{e}^{−U (x)} / \int_{\mathbb{R}^d} \mathrm{e}^{−U (y)}\mathrm{d}y$. Such problem naturally occurs for example in Bayesian inference and machine learning. Under the assumption that $U$ is continuously differentiable, $\nabla U$ is globally Lipschitz and $U$ is strongly convex, we obtain non-asymptotic bounds for the convergence to stationarity in Wasserstein distance of order $2$ and total variation distance of the sampling method based on the Euler discretization of the Langevin stochastic differential equation, for both constant and decreasing step sizes. The dependence on the dimension of the state space of the obtained bounds is studied to demonstrate the applicability of this method. The convergence of an appropriately weighted empirical measure is also investigated and bounds for the mean square error and exponential deviation inequality are reported for functions which are either Lipchitz continuous or measurable and bounded. An illustration to a Bayesian inference for binary regression is presented.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [39 references]  Display  Hide  Download
Contributor : Alain Durmus <>
Submitted on : Friday, December 9, 2016 - 3:24:34 AM
Last modification on : Tuesday, December 8, 2020 - 10:21:45 AM
Long-term archiving on: : Thursday, March 23, 2017 - 9:04:00 AM


Files produced by the author(s)


  • HAL Id : hal-01304430, version 2


Alain Durmus, Éric Moulines. High-dimensional Bayesian inference via the Unadjusted Langevin Algorithm. 2016. ⟨hal-01304430v2⟩



Record views


Files downloads