English
Related papers

Related papers: Regime-Switching Langevin Monte Carlo Algorithms

200 papers

We propose a novel Markov chain Monte-Carlo (MCMC) method for reverse engineering the topological structure of stochastic reaction networks, a notoriously challenging problem that is relevant in many modern areas of research, like…

Methodology · Statistics 2018-10-08 Daniel F. Linder , Grzegorz A. Rempala

Given a target function $H$ to minimize or a target Gibbs distribution $\pi_{\beta}^0 \propto e^{-\beta H}$ to sample from in the low temperature, in this paper we propose and analyze Langevin Monte Carlo (LMC) algorithms that run on an…

Probability · Mathematics 2023-02-09 Michael C. H. Choi , Youjia Wang

We study the efficiency of Thompson sampling for contextual bandits. Existing Thompson sampling-based algorithms need to construct a Laplace approximation (i.e., a Gaussian distribution) of the posterior distribution, which is inefficient…

Machine Learning · Computer Science 2022-06-23 Pan Xu , Hongkai Zheng , Eric Mazumdar , Kamyar Azizzadenesheli , Anima Anandkumar

Markov chain Monte Carlo (MCMC), such as Langevin dynamics, is valid for approximating intractable distributions. However, its usage is limited in the context of deep latent variable models owing to costly datapoint-wise sampling iterations…

Machine Learning · Computer Science 2022-10-12 Shohei Taniguchi , Yusuke Iwasawa , Wataru Kumagai , Yutaka Matsuo

Variable selection is a key issue when analyzing high-dimensional data. The explosion of data with large sample sizes and dimensionality brings new challenges to this problem in both inference accuracy and computational complexity. To…

Methodology · Statistics 2016-11-30 Xu Chen , Shaan Qamar , Surya T. Tokdar

Markov chain Monte Carlo methods have become standard tools in statistics to sample from complex probability measures. Many available techniques rely on discrete-time reversible Markov chains whose transition kernels build up over the…

Methodology · Statistics 2017-02-21 Alexandre Bouchard-Côté , Sebastian J. Vollmer , Arnaud Doucet

Numerous capability and safety techniques of Large Language Models (LLMs), including RLHF, automated red-teaming, prompt engineering, and infilling, can be cast as sampling from an unnormalized target distribution defined by a given reward…

Machine Learning · Computer Science 2024-05-01 Stephen Zhao , Rob Brekelmans , Alireza Makhzani , Roger Grosse

We propose an adaptively weighted stochastic gradient Langevin dynamics algorithm (SGLD), so-called contour stochastic gradient Langevin dynamics (CSGLD), for Bayesian learning in big data statistics. The proposed algorithm is essentially a…

Machine Learning · Statistics 2022-05-24 Wei Deng , Guang Lin , Faming Liang

Designing efficient learning algorithms with complexity guarantees for Markov decision processes (MDPs) with large or continuous state and action spaces remains a fundamental challenge. We address this challenge for entropy-regularized MDPs…

Machine Learning · Computer Science 2025-06-05 Matthieu Meunier , Christoph Reisinger , Yufei Zhang

We study the utility of a complex Langevin (CL) equation as an alternative for the Monte Carlo (MC) procedure in the evaluation of expectation values occurring in fermionic many-body problems. We find that a CL approach is natural in cases…

Nuclear Theory · Physics 2009-11-06 Chris Adami , Steven E. Koonin

We propose an algorithm for the efficient and robust sampling of the posterior probability distribution in Bayesian inference problems. The algorithm combines the local search capabilities of the Manifold Metropolis Adjusted Langevin…

While multilevel Monte Carlo (MLMC) methods for the numerical approximation of partial differential equations with random coefficients enjoy great popularity, combinations with spatial adaptivity seem to be rare. We present an adaptive MLMC…

Numerical Analysis · Mathematics 2017-12-20 Ralf Kornhuber , Evgenia Youett

In this paper, we explore a general Aggregated Gradient Langevin Dynamics framework (AGLD) for the Markov Chain Monte Carlo (MCMC) sampling. We investigate the nonasymptotic convergence of AGLD with a unified analysis for different data…

Machine Learning · Computer Science 2019-10-22 Chao Zhang , Jiahao Xie , Zebang Shen , Peilin Zhao , Tengfei Zhou , Hui Qian

This paper applies several well-known tricks from the numerical treatment of deterministic differential equations to improve the efficiency of the Multilevel Monte Carlo (MLMC) method for stochastic differential equations (SDEs) and…

Numerical Analysis · Mathematics 2014-12-23 Eike H. Mueller , Rob Scheichl , Tony Shardlow

We consider parallel asynchronous Markov Chain Monte Carlo (MCMC) sampling for problems where we can leverage (stochastic) gradients to define continuous dynamics which explore the target distribution. We outline a solution strategy for…

Machine Learning · Statistics 2016-12-09 Jost Tobias Springenberg , Aaron Klein , Stefan Falkner , Frank Hutter

We study the problem of approximate sampling from non-log-concave distributions, e.g., Gaussian mixtures, which is often challenging even in low dimensions due to their multimodality. We focus on performing this task via Markov chain Monte…

Machine Learning · Statistics 2024-05-30 Tim Tsz-Kit Lau , Han Liu , Thomas Pock

Proposals for Metropolis-Hastings MCMC derived by discretizing Langevin diffusion or Hamiltonian dynamics are examples of stochastic autoregressive proposals that form a natural wider class of proposals with equivalent computability. We…

Computation · Statistics 2016-10-05 Richard A. Norton , Colin Fox

Optimizing or sampling complex cost functions of combinatorial optimization problems is a longstanding challenge across disciplines and applications. When employing family of conventional algorithms based on Markov Chain Monte Carlo (MCMC)…

Machine Learning · Computer Science 2025-08-15 Dmitrii Dobrynin , Masoud Mohseni , John Paul Strachan

Distributionally Robust Reinforcement Learning (DR-RL) aims to derive a policy optimizing the worst-case performance within a predefined uncertainty set. Despite extensive research, previous DR-RL algorithms have predominantly favored…

Machine Learning · Computer Science 2024-06-26 Yudan Wang , Shaofeng Zou , Yue Wang

Classically, the continuous-time Langevin diffusion converges exponentially fast to its stationary distribution $\pi$ under the sole assumption that $\pi$ satisfies a Poincar\'e inequality. Using this fact to provide guarantees for the…

Statistics Theory · Mathematics 2024-07-11 Sinho Chewi , Murat A. Erdogdu , Mufan Bill Li , Ruoqi Shen , Matthew Zhang
‹ Prev 1 4 5 6 7 8 10 Next ›