English
Related papers

Related papers: Proximal Algorithms for Accelerated Langevin Dynam…

200 papers

Standard first-order Langevin algorithms such as the unadjusted Langevin algorithm (ULA) are obtained by discretizing the Langevin diffusion and are widely used for sampling in machine learning because they scale to high dimensions and…

Machine Learning · Statistics 2025-09-25 Mert Gurbuzbalaban , Hoang M. Nguyen , Xicheng Zhang , Lingjiong Zhu

We introduce a novel framework for efficient sampling from complex, unnormalised target distributions by exploiting multiscale dynamics. Traditional score-based sampling methods either rely on learned approximations of the score function or…

Computation · Statistics 2025-11-04 Paula Cordero-Encinar , Andrew B. Duncan , Sebastian Reich , O. Deniz Akyildiz

Various distributed gradient descent algorithms for multi-agent optimization have incorporated the Nesterov accelerated gradient method, where the use of momentum enhances convergence rates. These algorithms have found broad applications in…

Systems and Control · Electrical Eng. & Systems 2026-04-21 Zihao Ren , Lei Wang , Guodong Shi

Recent advances in stochastic gradient techniques have made it possible to estimate posterior distributions from large datasets via Markov Chain Monte Carlo (MCMC). However, when the target posterior is multimodal, mixing performance is…

Machine Learning · Statistics 2018-01-12 Yizhe Zhang , Changyou Chen , Zhe Gan , Ricardo Henao , Lawrence Carin

We propose a very fast approximate Markov Chain Monte Carlo (MCMC) sampling framework that is applicable to a large class of sparse Bayesian inference problems, where the computational cost per iteration in several models is of order…

Computation · Statistics 2021-08-17 Yves Atchadé , Liwei Wang

Particle MCMC is a class of algorithms that can be used to analyse state-space models. They use MCMC moves to update the parameters of the models, and particle filters to propose values for the path of the state-space model. Currently the…

Computation · Statistics 2014-12-25 Chris Nemeth , Paul Fearnhead

Nesterov's Accelerated Gradient (NAG) for optimization has better performance than its continuous time limit (noiseless kinetic Langevin) when a finite step-size is employed \citep{shi2021understanding}. This work explores the sampling…

Machine Learning · Computer Science 2022-06-22 Ruilin Li , Hongyuan Zha , Molei Tao

We introduce a new method to accurately and efficiently estimate the effective dynamics of collective variables in molecular simulations. Such reduced dynamics play an essential role in the study of a broad class of processes, ranging from…

Statistical Mechanics · Physics 2022-03-28 Hadrien Vroylandt , Ludovic Goudenège , Pierre Monmarché , Fabio Pietrucci , Benjamin Rotenberg

Probably one of the most striking examples of the close connections between global optimization processes and statistical physics is the simulated annealing method, inspired by the famous Monte Carlo algorithm devised by Metropolis et al.…

Numerical Analysis · Mathematics 2024-01-12 Lorenzo Pareschi

We study numerical methods for sampling probability measures in high dimension where the underlying model is only approximately identified with a gradient system. Extended stochastic dynamical methods are discussed which have application to…

Numerical Analysis · Mathematics 2016-03-08 Benedict Leimkuhler , Xiaocheng Shang

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

This paper is concerned with the approximation to invariant measures for Langevin dynamics of McKean--Vlasov type. Under dissipativity and Lipschitz conditions, we prove that the empirical measures of both the mean-field and…

Probability · Mathematics 2024-04-30 Wenjing Cao , Kai Du

We consider the inverse problem of reconstructing the posterior measure over the trajec- tories of a diffusion process from discrete time observations and continuous time constraints. We cast the problem in a Bayesian framework and derive…

Machine Learning · Statistics 2016-12-21 Botond Cseke , David Schnoerr , Manfred Opper , Guido Sanguinetti

We present a highly efficient proximal Markov chain Monte Carlo methodology to perform Bayesian computation in imaging problems. Similarly to previous proximal Monte Carlo approaches, the proposed method is derived from an approximation of…

Computation · Statistics 2020-03-20 Luis Vargas , Marcelo Pereyra , Konstantinos C. Zygalakis

Markov chain Monte Carlo (MCMC) methods are one of the most popular classes of algorithms for sampling from a target probability distribution. A rising trend in recent years consists in analyzing the convergence of MCMC algorithms using…

Probability · Mathematics 2025-04-30 Federica Milinanni

In this work we consider the unbiased estimation of expectations w.r.t.~probability measures that have non-negative Lebesgue density, and which are known point-wise up-to a normalizing constant. We focus upon developing an unbiased method…

Computation · Statistics 2023-08-17 Hamza Ruzayqat , Neil K. Chada , Ajay Jasra

The purpose of this paper is to examine the Lagrangian stochastic modeling of the fluid velocity seen by inertial particles in a nonhomogeneous turbulent flow. A new Langevin-type model, compatible with the transport equation of the drift…

Fluid Dynamics · Physics 2009-07-01 Boris Arcen , Anne Tanière

Replica exchange stochastic gradient Langevin dynamics (reSGLD) has shown promise in accelerating the convergence in non-convex learning; however, an excessively large correction for avoiding biases from noisy energy estimators has limited…

Machine Learning · Statistics 2021-03-19 Wei Deng , Qi Feng , Georgios Karagiannis , Guang Lin , Faming Liang

We introduce a gradient-based learning method to automatically adapt Markov chain Monte Carlo (MCMC) proposal distributions to intractable targets. We define a maximum entropy regularised objective function, referred to as generalised speed…

Machine Learning · Statistics 2020-01-07 Michalis K. Titsias , Petros Dellaportas

The Pseudo-Marginal (PM) algorithm is a popular Markov chain Monte Carlo (MCMC) method used to sample from a target distribution when its density is inaccessible, but can be estimated with a non-negative unbiased estimator. Its performance…

Computation · Statistics 2025-09-30 Sarra Abaoubida , Mylène Bédard , Florian Maire
‹ Prev 1 4 5 6 7 8 10 Next ›