# Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm

@article{Durmus2015NonasymptoticCA, title={Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithm}, author={Alain Durmus and {\'E}ric Moulines}, journal={arXiv: Statistics Theory}, year={2015} }

In this paper, we study a method to sample from a target distribution $\pi$ over $\mathbb{R}^d$ having a positive density with respect to the Lebesgue measure, known up to a normalisation factor. This method is based on the Euler discretization of the overdamped Langevin stochastic differential equation associated with $\pi$. For both constant and decreasing step sizes in the Euler discretization, we obtain non-asymptotic bounds for the convergence to the target distribution $\pi$ in total…

## 255 Citations

Improved bounds for discretization of Langevin diffusions: Near-optimal rates without convexity

- Computer Science
- 2019

An improved analysis of the Euler-Maruyama discretization of the Langevin diffusion does not require global contractivity, and yields polynomial dependence on the time horizon, and simultaneously improves all those methods based on Dalayan's approach.

Mean-Square Analysis with An Application to Optimal Dimension Dependence of Langevin Monte Carlo

- Computer Science
- 2021

This work provides a general framework for the non-asymptotic analysis of sampling error in 2-Wasserstein distance, which also leads to a bound of mixing time, which is optimal in both dimension d and accuracy tolerance for target measures satisfying the aforementioned assumptions.

Analysis of Langevin Monte Carlo via Convex Optimization

- Computer ScienceJ. Mach. Learn. Res.
- 2019

It is shown that the Unadjusted Langevin Algorithm can be formulated as a first order optimization algorithm of an objective functional defined on the Wasserstein space of order $2$ and a non-asymptotic analysis of this method to sample from logconcave smooth target distribution is given.

Wasserstein distance estimates for the distributions of numerical approximations to ergodic stochastic differential equations

- MathematicsJ. Mach. Learn. Res.
- 2021

We present a framework that allows for the non-asymptotic study of the 2-Wasserstein distance between the invariant distribution of an ergodic stochastic differential equation and the distribution of…

Asymptotic bias of inexact Markov Chain Monte Carlo methods in high dimension

- Computer ScienceArXiv
- 2021

This paper establishes non-asymptotic bounds on Wasserstein distances between the invariant probability measures of inexact MCMC methods and their target distribution and shows that the dimension dependence relies on some key quantities.

The Forward-Backward Envelope for Sampling with the Overdamped Langevin Algorithm

- MathematicsArXiv
- 2022

In this paper, we analyse a proximal method based on the idea of forward-backward splitting for sampling from distributions with densities that are not necessarily smooth. In particular, we study the…

Higher order Langevin Monte Carlo algorithm

- Computer ScienceElectronic Journal of Statistics
- 2019

A new Langevin Monte Carlo (LMC) algorithm with improved rates in total variation and in Wasserstein distance is presented and non-asymptotic bounds are obtained for the convergence to stationarity of the new sampling method.

Implicit Langevin Algorithms for Sampling From Log-concave Densities

- Computer Science, MathematicsJ. Mach. Learn. Res.
- 2021

This work proves geometric ergodicity and stability of the resulting methods for all step sizes and shows that obtaining subsequent samples amounts to solving a strongly-convex optimization problem, which is readily achievable using one of numerous existing methods.

Uniform minorization condition and convergence bounds for discretizations of kinetic Langevin dynamics

- Mathematics, Computer ScienceArXiv
- 2021

The convergence in total variation and V -norm of discretization schemes of the underdamped Langevin dynamics is studied to derive geometric convergence bounds and estimates on norms of solutions to Poisson equations associated with a given scheme.

Sampling from a strongly log-concave distribution with the Unadjusted Langevin Algorithm

- Mathematics
- 2016

We consider in this paper the problem of sampling a probability distribution π having a density w.r.t. the Lebesgue measure on $\mathbb{R}^d$, known up to a normalisation factor $x \mapsto…

## References

SHOWING 1-10 OF 51 REFERENCES

On Some non Asymptotic Bounds for the Euler Scheme

- Computer Science, Mathematics
- 2010

Non asymptotic bounds for the Monte Carlo algorithm associated to the Euler discretization of some diffusion processes are obtained from a Gaussian upper bound of the density of the scheme and a modification of the so-called "Herbst argument" used to prove Logarithmic Sobolev inequalities.

Rate of convergence for ergodic continuous Markov processes : Lyapunov versus Poincaré

- Mathematics
- 2007

Rates of convergence of stochastically monotone and continuous time Markov models

- Mathematics
- 2000

In this paper we give bounds on the total variation distance from convergence of a continuous time positive recurrent Markov process on an arbitrary state space, based on Foster-Lyapunov drift and…

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

- Mathematics, Computer Science
- 2014

This work establishes non‐asymptotic bounds for the error of approximating the target distribution by the distribution obtained by the Langevin Monte Carlo method and its variants and illustrates the effectiveness of the established guarantees.

Trends to equilibrium in total variation distance

- Mathematics
- 2007

This paper presents different approaches, based on functional inequalities, to study the speed of convergence in total variation distance of ergodic diffusion processes with initial law satisfying a…

The geometry of logconcave functions and sampling algorithms

- Computer Science, MathematicsRandom Struct. Algorithms
- 2007

These results are applied to analyze two efficient algorithms for sampling from a logconcave distribution in n dimensions, with no assumptions on the local smoothness of the density function.

Expansion of the global error for numerical schemes solving stochastic differential equations

- Mathematics
- 1990

Given the solution (Xt ) of a Stochastic Differential System, two situat,ions are considered: computat,ion of Ef(Xt ) by a Monte–Carlo method and, in the ergodic case, integration of a function f…

Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise

- Mathematics
- 2002

Reflection couplings and contraction rates for diffusions

- Mathematics
- 2016

We consider contractivity for diffusion semigroups w.r.t. Kantorovich ($$L^1$$L1 Wasserstein) distances based on appropriately chosen concave functions. These distances are inbetween total variation…