English
Related papers

Related papers: Optimal dimension dependence of the Metropolis-Adj…

200 papers

In this paper we study the asymptotic behavior of the Random-Walk Metropolis algorithm on probability densities with two different `scales', where most of the probability mass is distributed along certain key directions with the…

Computation · Statistics 2015-10-12 Alexandros Beskos , Gareth Roberts , Alexandre Thiery , Natesh Pillai

Deterministic-scan and random-scan component-wise Markov chain Monte Carlo algorithms, such as Gibbs samplers and conditional Metropolis-Hastings, are popular approaches for sampling from multivariate distributions. A long-standing open…

Statistics Theory · Mathematics 2026-04-28 Youngwoo Kwon , Galin Jones , Qian Qin

The computational complexity of internal diffusion-limited aggregation (DLA) is examined from both a theoretical and a practical point of view. We show that for two or more dimensions, the problem of predicting the cluster from a given set…

Condensed Matter · Physics 2007-05-23 Cristopher Moore , Jonathan Machta

We develop a class of interacting particle systems for implementing a maximum marginal likelihood estimation (MMLE) procedure to estimate the parameters of a latent variable model. We achieve this by formulating a continuous-time…

Convergence analysis of Markov chain Monte Carlo methods in high-dimensional statistical applications is increasingly recognized. In this paper, we develop general mixing time bounds for Metropolis-Hastings algorithms on discrete spaces by…

Computation · Statistics 2025-07-29 Hyunwoong Chang , Quan Zhou

We present an improved analysis of the Euler-Maruyama discretization of the Langevin diffusion. Our analysis does not require global contractivity, and yields polynomial dependence on the time horizon. Compared to existing approaches, we…

Probability · Mathematics 2019-11-05 Wenlong Mou , Nicolas Flammarion , Martin J. Wainwright , Peter L. Bartlett

We consider the problem of sampling from a high-dimensional target distribution $\pi_\beta$ on $\mathbb{R}^d$ with density proportional to $\theta\mapsto e^{-\beta U(\theta)}$ using explicit numerical schemes based on discretising the…

Probability · Mathematics 2024-06-13 Ariel Neufeld , Matthew Ng Cheng En , Ying Zhang

We show that any randomised Monte Carlo distributed algorithm for the Lov\'asz local lemma requires $\Omega(\log \log n)$ communication rounds, assuming that it finds a correct assignment with high probability. Our result holds even in the…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-11-04 Sebastian Brandt , Orr Fischer , Juho Hirvonen , Barbara Keller , Tuomo Lempiäinen , Joel Rybicki , Jukka Suomela , Jara Uitto

Optimal scaling has been well studied for Metropolis-Hastings (M-H) algorithms in continuous spaces, but a similar understanding has been lacking in discrete spaces. Recently, a family of locally balanced proposals (LBP) for discrete spaces…

Machine Learning · Computer Science 2022-10-17 Haoran Sun , Hanjun Dai , Dale Schuurmans

A well-known first-order method for sampling from log-concave probability distributions is the Unadjusted Langevin Algorithm (ULA). This work proposes a new annealing step-size schedule for ULA, which allows to prove new convergence…

Statistics Theory · Mathematics 2020-07-03 Paul Rolland , Armin Eftekhari , Ali Kavis , Volkan Cevher

This work extends Roberts et al. (1997) by considering limits of Random Walk Metropolis (RWM) applied to block IID target distributions, with corresponding block-independent proposals. The extension verifies the robustness of the optimal…

Probability · Mathematics 2019-02-19 Jeffrey Negrea

Denoising diffusions are a powerful method to generate approximate samples from high-dimensional data distributions. Recent results provide polynomial bounds on their convergence rate, assuming $L^2$-accurate scores. Until now, the tightest…

Machine Learning · Statistics 2024-03-07 Joe Benton , Valentin De Bortoli , Arnaud Doucet , George Deligiannidis

Recent work on backpropagation-free learning has shown that it is possible to use forward-mode automatic differentiation (AD) to perform optimization on differentiable models. Forward-mode AD requires sampling a tangent vector for each…

Machine Learning · Computer Science 2025-05-26 Adam D. Cobb , Susmit Jha

The unadjusted Langevin algorithm is commonly used to sample probability distributions in extremely high-dimensional settings. However, existing analyses of the algorithm for strongly log-concave distributions suggest that, as the dimension…

Machine Learning · Statistics 2025-09-05 Yifan Chen , Xiaoou Cheng , Jonathan Niles-Weed , Jonathan Weare

We study an overdamped Langevin equation on the $d$-dimensional torus with stationary distribution proportional to~$p = e^{-U / \kappa}$. When~$U$ has multiple wells the mixing time of the associated process is exponentially large (of…

Probability · Mathematics 2023-09-06 Alexander Christie , Yuanyuan Feng , Gautam Iyer , Alexei Novikov

We propose a new method called the Metropolis-adjusted Mirror Langevin algorithm for approximate sampling from distributions whose support is a compact and convex set. This algorithm adds an accept-reject filter to the Markov chain induced…

Computation · Statistics 2024-06-24 Vishwak Srinivasan , Andre Wibisono , Ashia Wilson

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

Let $G$ be a graph on $n$ vertices of maximum degree $\Delta$. We show that, for any $\delta > 0$, the down-up walk on independent sets of size $k \leq (1-\delta)\alpha_c(\Delta)n$ mixes in time $O_{\Delta,\delta}(k\log{n})$, thereby…

Data Structures and Algorithms · Computer Science 2023-05-11 Vishesh Jain , Marcus Michelen , Huy Tuan Pham , Thuy-Duong Vuong

We introduce a new family of MCMC samplers that combine auxiliary variables, Gibbs sampling and Taylor expansions of the target density. Our approach permits the marginalisation over the auxiliary variables yielding marginal samplers, or…

Machine Learning · Statistics 2018-01-26 Michalis K. Titsias , Omiros Papaspiliopoulos

We introduce MALT: a new Metropolis adjusted sampler built upon the (kinetic) Langevin diffusion. Compared to Generalized Hamiltonian Monte Carlo (GHMC), the Metropolis correction is applied to whole Langevin trajectories, which prevents…

Computation · Statistics 2023-12-12 Lionel Riou-Durand , Jure Vogrinc