English
Related papers

Related papers: Log-concave sampling: Metropolis-Hastings algorith…

200 papers

We consider the problem of sampling from a strongly log-concave density in $\mathbb{R}^d$, and prove an information theoretic lower bound on the number of stochastic gradient queries of the log density needed. Several popular sampling…

Machine Learning · Statistics 2021-07-06 Niladri S. Chatterji , Peter L. Bartlett , Philip M. Long

We prove explicit, i.e., non-asymptotic, error bounds for Markov Chain Monte Carlo methods, such as the Metropolis algorithm. The problem is to compute the expectation (or integral) of f with respect to a measure which can be given by a…

Numerical Analysis · Mathematics 2011-01-18 Daniel Rudolf

Recent advances in stochastic optimization have yielded the interacting particle Langevin algorithm (IPLA), which leverages the notion of interacting particle systems (IPS) to efficiently sample from approximate posterior densities. This…

Probability · Mathematics 2025-06-04 Tim Johnston , Nikolaos Makras , Sotirios Sabanis

We consider the problem of sampling from a density of the form $p(x) \propto \exp(-f(x)- g(x))$, where $f: \mathbb{R}^d \rightarrow \mathbb{R}$ is a smooth and strongly convex function and $g: \mathbb{R}^d \rightarrow \mathbb{R}$ is a…

Machine Learning · Statistics 2019-10-02 Wenlong Mou , Nicolas Flammarion , Martin J. Wainwright , Peter L. Bartlett

We introduce a new framework for efficient sampling from complex probability distributions, using a combination of optimal transport maps and the Metropolis-Hastings rule. The core idea is to use continuous transportation to transform…

Computation · Statistics 2019-06-11 Matthew Parno , Youssef Marzouk

We study the problem of learning multivariate log-concave densities with respect to a global loss function. We obtain the first upper bound on the sample complexity of the maximum likelihood estimator (MLE) for a log-concave density on…

Statistics Theory · Mathematics 2018-12-06 Timothy Carpenter , Ilias Diakonikolas , Anastasios Sidiropoulos , Alistair Stewart

Markov chain Monte Carlo samplers based on discretizations of (overdamped) Langevin dynamics are commonly used in the Bayesian inference and computational statistical physics literature to estimate high-dimensional integrals. One can…

Numerical Analysis · Mathematics 2025-08-11 Tony Lelièvre , Régis Santet , Gabriel Stoltz

We establish the first tight lower bound of $\Omega(\log\log\kappa)$ on the query complexity of sampling from the class of strongly log-concave and log-smooth distributions with condition number $\kappa$ in one dimension. Whereas existing…

Statistics Theory · Mathematics 2021-06-11 Sinho Chewi , Patrik Gerber , Chen Lu , Thibaut Le Gouic , Philippe Rigollet

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

The complexity of the Metropolis-Hastings (MH) algorithm arises from the requirement of a likelihood evaluation for the full data set in each iteration. Payne and Mallick (2015) propose to speed up the algorithm by a delayed acceptance…

Computation · Statistics 2017-03-23 Matias Quiroz , Minh-Ngoc Tran , Mattias Villani , Robert Kohn

High-dimensional limit theorems have been shown useful to derive tuning rules for finding the optimal scaling in random-walk Metropolis algorithms. The assumptions under which weak convergence results are proved are however restrictive: the…

Methodology · Statistics 2022-02-16 Sebastian M Schmon , Philippe Gagnon

Sampling a random permutation with restricted positions, or equivalently approximating the permanent of a 0-1 matrix, is a fundamental problem in computer science, with several notable results achieved over the years. However, existing…

Data Structures and Algorithms · Computer Science 2025-08-15 Kun He , Guoliang Qiu , Xiaoming Sun

Equality-constrained models naturally arise in problems in which measurements are taken at different levels of resolution. The challenge in this setting is that the models usually induce a joint distribution which is intractable. Resorting…

Computation · Statistics 2025-04-28 Shenggang Hu , Hongsheng Dai , Fanlin Meng , Louis Aslett , Murray Pollock , Gareth O. Roberts

Acceleration is a celebrated cornerstone of convex optimization, enabling gradient-based algorithms to converge sublinearly in the condition number. A major open question is whether an analogous acceleration phenomenon is possible for…

Probability · Mathematics 2026-04-01 Jason M. Altschuler , Sinho Chewi , Matthew S. Zhang

We analyse computational efficiency of Metropolis-Hastings algorithms with AR(1) process proposals. These proposals include, as a subclass, discretized Langevin diffusion (e.g. MALA) and discretized Hamiltonian dynamics (e.g. HMC). By…

Probability · Mathematics 2015-01-15 Richard A. Norton , Colin Fox

We aim to improve upon the exploration of the general-purpose random walk Metropolis algorithm when the target has non-convex support $A \subset \mathbb{R}^d$, by reusing proposals in $A^c$ which would otherwise be rejected. The algorithm…

Probability · Mathematics 2021-08-17 John Moriarty , Jure Vogrinc , Alessandro Zocca

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

Motivated by applications in deep learning, where the global Lipschitz continuity condition is often not satisfied, we examine the problem of sampling from distributions with super-linearly growing log-gradients. We propose a novel tamed…

Statistics Theory · Mathematics 2025-06-06 Iosif Lytras , Sotirios Sabanis , Ying Zhang

Markov Chain Monte Carlo (MCMC) algorithms are commonly used for their versatility in sampling from complicated probability distributions. However, as the dimension of the distribution gets larger, the computational costs for a satisfactory…

Cosmology and Nongalactic Astrophysics · Physics 2020-12-01 Hector J. Hortua , Riccardo Volpi , Dimitri Marinelli , Luigi Malago

Yang et al. (2016) proved that the symmetric random walk Metropolis--Hastings algorithm for Bayesian variable selection is rapidly mixing under mild high-dimensional assumptions. We propose a novel MCMC sampler using an informed proposal…

Methodology · Statistics 2022-04-26 Quan Zhou , Jun Yang , Dootika Vats , Gareth O. Roberts , Jeffrey S. Rosenthal