English
Related papers

Related papers: Sampling and estimation on manifolds using the Lan…

200 papers

We study the problem of estimating a distribution over a finite alphabet from an i.i.d. sample, with accuracy measured in relative entropy (Kullback-Leibler divergence). While optimal bounds on the expected risk are known, high-probability…

Statistics Theory · Mathematics 2026-02-27 Jaouad Mourtada

We propose a Markov chain Monte Carlo (MCMC) algorithm based on third-order Langevin dynamics for sampling from distributions with log-concave and smooth densities. The higher-order dynamics allow for more flexible discretization schemes,…

Machine Learning · Statistics 2020-05-27 Wenlong Mou , Yi-An Ma , Martin J. Wainwright , Peter L. Bartlett , Michael I. Jordan

We provide new convergence guarantees in Wasserstein distance for diffusion-based generative models, covering both stochastic (DDPM-like) and deterministic (DDIM-like) sampling methods. We introduce a simple framework to analyze…

Machine Learning · Computer Science 2025-11-14 Eliot Beyler , Francis Bach

We present a novel method for drawing samples from Gibbs distributions with densities of the form $\pi(x) \propto \exp(-U(x))$. The method accelerates the unadjusted Langevin algorithm by introducing an inertia term similar to Polyak's…

Numerical Analysis · Mathematics 2025-10-09 Alexander Falk , Andreas Habring , Christoph Griesbacher , Thomas Pock

Algorithms based on discretizing Langevin diffusion are popular tools for sampling from high-dimensional distributions. We develop novel connections between such Monte Carlo algorithms, the theory of Wasserstein gradient flow, and the…

Computation · Statistics 2019-05-13 Espen Bernton

The Metropolis-adjusted Langevin (MALA) algorithm is a sampling algorithm which makes local moves by incorporating information about the gradient of the logarithm of the target density. In this paper we study the efficiency of MALA on a…

Probability · Mathematics 2012-11-29 Natesh S. Pillai , Andrew M. Stuart , Alexandre H. Thiéry

Underdamped Langevin Monte Carlo (ULMC) is an algorithm used to sample from unnormalized densities by leveraging the momentum of a particle moving in a potential well. We provide a novel analysis of ULMC, motivated by two central questions:…

Statistics Theory · Mathematics 2023-02-17 Matthew Zhang , Sinho Chewi , Mufan Bill Li , Krishnakumar Balasubramanian , Murat A. Erdogdu

The measured time series from complex systems are renowned for their intricate stochastic behavior, characterized by random fluctuations stemming from external influences and nonlinear interactions. These fluctuations take diverse forms,…

Statistical Mechanics · Physics 2025-03-19 Pyei Phyo Lin , Matthias Wächter , Joachim Peinke , M. Reza Rahimi Tabar

Score-based diffusion methods provide a powerful strategy to solve image restoration tasks by flexibly combining a pre-trained foundational prior model with a likelihood function specified during test time. Such methods are predominantly…

Computer Vision and Pattern Recognition · Computer Science 2024-09-09 Charlesquin Kemajou Mbakam , Jean-Francois Giovannelli , Marcelo Pereyra

We examine the Langevin diffusion confined to a closed, convex domain $D\subset\mathbb{R}^d$, represented as a reflected stochastic differential equation. We introduce a sequence of penalized stochastic differential equations and prove that…

Probability · Mathematics 2026-01-22 Tarika Mane , Amine Boukardagha

Sampling from unnormalized target distributions is a fundamental yet challenging task in machine learning and statistics. Existing sampling algorithms typically require many iterative steps to produce high-quality samples, leading to high…

Machine Learning · Statistics 2026-02-27 Pascal Jutras-Dube , Jiaru Zhang , Ziran Wang , Ruqi Zhang

Many methods that build powerful variational distributions based on unadjusted Langevin transitions exist. Most of these were developed using a wide range of different approaches and techniques. Unfortunately, the lack of a unified analysis…

Machine Learning · Computer Science 2023-03-24 Tomas Geffner , Justin Domke

In this article we consider the estimation of static parameters for partially observed diffusion process with discrete-time observations over a fixed time interval. In particular, we assume that one must time-discretize the partially…

Computation · Statistics 2023-09-20 Elsiddig Awadelkarim , Ajay Jasra , Hamza Ruzayqat

Sampling from learned high-dimensional distributions is a foundational computational problem. We introduce U-turn chains: Markov chains obtained by iterating short forward-backward steps of a diffusion model, in which each step proposes a…

Machine Learning · Computer Science 2026-05-27 Hyunmo Kang , Noam Itzhak Levi , Corinna Elena Wegner , Daniel J. Korchinski , Matthieu Wyart

We provide a clarification of the description of Langevin diffusions on Riemannian manifolds and of the measure underlying the invariant density. As a result we propose a new position-dependent Metropolis-adjusted Langevin algorithm (MALA)…

Methodology · Statistics 2014-08-15 Tatiana Xifara , Chris Sherlock , Samuel Livingstone , Simon Byrne , Mark Girolami

This work considers the problem of sampling from a probability distribution known up to a normalization constant while satisfying a set of statistical constraints specified by the expected values of general nonlinear functions. This problem…

Machine Learning · Statistics 2025-01-08 Luiz F. O. Chamon , Mohammad Reza Karimi , Anna Korba

The Metropolis-adjusted Langevin algorithm (MALA) is a Metropolis-Hastings method for approximate sampling from continuous distributions. We derive upper bounds for the contraction rate in Kantorovich-Rubinstein-Wasserstein distance of the…

Probability · Mathematics 2014-01-17 Andreas Eberle

Group-invariant probability distributions appear in many data-generative models in machine learning, such as graphs, point clouds, and images. In practice, one often needs to estimate divergences between such distributions. In this work, we…

Machine Learning · Computer Science 2026-02-05 Behrooz Tahmasebi , Stefanie Jegelka

This paper is concerned with sampling from probability distributions $\pi$ on $\mathbb{R}^d$ admitting a density of the form $\pi(x) \propto e^{-U(x)}$, where $U(x)=F(x)+G(Kx)$ with $K$ being a linear operator and $G$ being…

Optimization and Control · Mathematics 2024-05-28 Andreas Habring , Martin Holler , Thomas Pock

Diffusion models have demonstrated remarkable performance in generating high-dimensional samples across domains such as vision, language, and the sciences. Although continuous-state diffusion models have been extensively studied both…

Machine Learning · Computer Science 2026-02-17 Aadithya Srikanth , Mudit Gaur , Vaneet Aggarwal