English
Related papers

Related papers: Constrained Dikin-Langevin diffusion for polyhedra

200 papers

Discretization of continuous-time diffusion processes is a widely recognized method for sampling. However, it seems to be a considerable restriction when the potentials are often required to be smooth (gradient Lipschitz). This paper…

Computation · Statistics 2022-02-23 Dao Nguyen

We introduce numerical methods for simulating the diffusive motion of rigid bodies of arbitrary shape immersed in a viscous fluid. We parameterize the orientation of the bodies using normalized quaternions, which are numerically robust,…

Soft Condensed Matter · Physics 2015-10-28 Steven Delong , Florencio Balboa Usabiaga , Aleksandar Donev

Various Markov chain Monte Carlo (MCMC) methods are studied to improve upon random walk Metropolis sampling, for simulation from complex distributions. Examples include Metropolis-adjusted Langevin algorithms, Hamiltonian Monte Carlo, and…

Computation · Statistics 2020-05-19 Zexi Song , Zhiqiang Tan

Motivated by decentralized approaches to machine learning, we propose a collaborative Bayesian learning algorithm taking the form of decentralized Langevin dynamics in a non-convex setting. Our analysis show that the initial KL-divergence…

Machine Learning · Statistics 2021-01-12 Anjaly Parayil , He Bai , Jemin George , Prudhvi Gurram

We propose a method for efficiently incorporating constraints into a stochastic gradient Langevin framework for the training of deep neural networks. Constraints allow direct control of the parameter space of the model. Appropriately…

Machine Learning · Computer Science 2021-06-22 Benedict Leimkuhler , Timothée Pouchon , Tiffany Vlaar , Amos Storkey

We introduce shielded Langevin Monte Carlo (LMC), a constrained sampler inspired by navigation functions, capable of sampling from unnormalized target distributions defined over punctured supports. In other words, this approach samples from…

Computation · Statistics 2025-12-30 Nicolas Zilberstein , Santiago Segarra , Luiz Chamon

Langevin MCMC gradient optimization is a class of increasingly popular methods for estimating a posterior distribution. This paper addresses the algorithm as applied in a decentralized setting, wherein data is distributed across a network…

Optimization and Control · Mathematics 2020-09-22 Vyacheslav Kungurtsev

We introduce a general framework that constructs estimators with reduced variance for random walk Metropolis and Metropolis-adjusted Langevin algorithms. The resulting estimators require negligible computational cost and are derived in a…

Methodology · Statistics 2022-03-07 Angelos Alexopoulos , Petros Dellaportas , Michalis K. Titsias

There has been considerable interest in designing Markov chain Monte Carlo algorithms by exploiting numerical methods for Langevin dynamics, which includes Hamiltonian dynamics as a deterministic case. A prominent approach is Hamiltonian…

Computation · Statistics 2021-06-08 Zexi Song , Zhiqiang Tan

Discretizations of Langevin diffusions provide a powerful method for sampling and Bayesian inference. However, such discretizations require evaluation of the gradient of the potential function. In several real-world scenarios, obtaining…

Statistics Theory · Mathematics 2021-01-19 Abhishek Roy , Lingqing Shen , Krishnakumar Balasubramanian , Saeed Ghadimi

While gradient-based discrete samplers are effective in sampling from complex distributions, they are susceptible to getting trapped in local minima, particularly in high-dimensional, multimodal discrete distributions, owing to the…

Machine Learning · Statistics 2025-05-21 Luxu Liang , Yuhang Jia , Feng Zhou

Generative modeling within constrained sets is essential for scientific and engineering applications involving physical, geometric, or safety requirements (e.g., molecular generation, robotics). We present a unified framework for…

Machine Learning · Computer Science 2026-04-21 Kijung Jeon , Michael Muehlebach , Molei Tao

We consider the random walk Metropolis algorithm on $\mathbb{R}^n$ with Gaussian proposals, and when the target probability measure is the $n$-fold product of a one-dimensional law. In the limit $n\to\infty$, it is well known (see [Ann.…

Probability · Mathematics 2016-08-14 Benjamin Jourdain , Tony Lelièvre , Błażej Miasojedow

The Langevin sampling method relies on an accurate score matching while the existing massive multiple-input multiple output (MIMO) Langevin detection involves an inevitable singular value decomposition (SVD) to calculate the posterior…

Signal Processing · Electrical Eng. & Systems 2024-04-23 Lanxin He , Zheng Wang , Yongming Huang

We study zero-shot conditional sampling with pretrained diffusion models for linear inverse problems, including inpainting and super-resolution. In these problems, the observation determines only part of the unknown signal. The remaining…

Machine Learning · Computer Science 2026-05-08 Ahmad Aghapour , Erhan Bayraktar , Asaf Cohen

Markov Chain Monte Carlo (MCMC) is one of the most powerful methods to sample from a given probability distribution, of which the Metropolis Adjusted Langevin Algorithm (MALA) is a variant wherein the gradient of the distribution is used…

Applications · Statistics 2022-01-21 Mariya Mamajiwala , Debasish Roy , Serge Guillas

We study a sequential Monte Carlo algorithm to sample from the Gibbs measure with a non-convex energy function at a low temperature. We use the practical and popular geometric annealing schedule, and use a Langevin diffusion at each…

Statistics Theory · Mathematics 2026-01-13 Ruiyu Han , Gautam Iyer , Dejan Slepčev

Diffusion models are a state-of-the-art generative modeling framework that transform noise to images via Langevin sampling, guided by the score, which is the gradient of the logarithm of the data distribution. Recent works have shown…

Machine Learning · Computer Science 2025-08-01 Aadithya Srikanth , Siddarth Asokan , Nishanth Shetty , Chandra Sekhar Seelamantula

In this article we consider sampling from log concave distributions in Hamiltonian setting, without assuming that the objective gradient is globally Lipschitz. We propose two algorithms based on monotone polygonal (tamed) Euler schemes, to…

Probability · Mathematics 2023-01-20 Tim Johnston , Iosif Lytras , Sotirios Sabanis

The exact estimation of latent variable models with big data is known to be challenging. The latents have to be integrated out numerically, and the dimension of the latent variables increases with the sample size. This paper develops a…

Econometrics · Economics 2023-06-27 Ruben Loaiza-Maya , Didier Nibbering , Dan Zhu