中文
相关论文

相关论文: Minimax Mixing Time of the Metropolis-Adjusted Lan…

200 篇论文

We show that the gradient norm $\|\nabla f(x)\|$ for $x \sim \exp(-f(x))$, where $f$ is strongly convex and smooth, concentrates tightly around its mean. This removes a barrier in the prior state-of-the-art analysis for the well-studied…

机器学习 · 计算机科学 2020-06-16 Yin Tat Lee , Ruoqi Shen , Kevin Tian

Uncertainty estimation is a key issue when considering the application of deep neural network methods in science and engineering. In this work, we introduce a novel algorithm that quantifies epistemic uncertainty via Monte Carlo sampling…

机器学习 · 统计学 2024-12-06 Sebastian Bieringer , Gregor Kasieczka , Maximilian F. Steffen , Mathias Trabs

While the Metropolis Adjusted Langevin Algorithm (MALA) is a popular and widely used Markov chain Monte Carlo method, very few papers derive conditions that ensure its convergence. In particular, to the authors' knowledge, assumptions that…

统计计算 · 统计学 2022-01-07 Alain Durmus , Éric Moulines

We analyze the mixing time of Metropolized Hamiltonian Monte Carlo (HMC) with the leapfrog integrator to sample from a distribution on $\mathbb{R}^d$ whose log-density is smooth, has Lipschitz Hessian in Frobenius norm and satisfies…

统计计算 · 统计学 2026-02-12 Yuansi Chen , Khashayar Gatmiry , Minhui Jiang

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…

应用统计 · 统计学 2022-01-21 Mariya Mamajiwala , Debasish Roy , Serge Guillas

It is well known in many settings that reversible Langevin diffusions in confining potentials converge to equilibrium exponentially fast. Adding irreversible perturbations to the drift of a Langevin diffusion that maintain the same…

统计方法学 · 统计学 2019-07-02 Michela Ottobre , Natesh S. Pillai , Konstantinos Spiliopoulos

The Metropolis-Adjusted Langevin Algorithm (MALA) is a Markov Chain Monte Carlo method which creates a Markov chain reversible with respect to a given target distribution, pi^N, with Lebesgue density on R^N; it can hence be used to…

概率论 · 数学 2017-08-24 J. Kuntz , M. Ottobre , A. M. Stuart

We extend the Langevin Monte Carlo (LMC) algorithm to compactly supported measures via a projection step, akin to projected Stochastic Gradient Descent (SGD). We show that (projected) LMC allows to sample in polynomial time from a…

概率论 · 数学 2016-08-08 Sébastien Bubeck , Ronen Eldan , Joseph Lehec

The usage of positive definite metric tensors derived from second derivative information in the context of the simplified manifold Metropolis adjusted Langevin algorithm (MALA) is explored. A new adaptive step length procedure that resolves…

统计计算 · 统计学 2015-09-03 Tore Selland Kleppe

We establish conditions under which Metropolis-Hastings (MH) algorithms with a position-dependent proposal covariance matrix will or will not have the geometric rate of convergence. Some of the diffusions based MH algorithms like the…

统计方法学 · 统计学 2022-08-23 Vivekananda Roy , Lijin Zhang

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…

统计计算 · 统计学 2024-06-24 Vishwak Srinivasan , Andre Wibisono , Ashia Wilson

Sampling from log-concave distributions is a well researched problem that has many applications in statistics and machine learning. We study the distributions of the form $p^{*}\propto\exp(-f(x))$, where…

机器学习 · 计算机科学 2019-09-13 Ruoqi Shen , Yin Tat Lee

We consider a recently proposed class of MCMC methods which uses proximity maps instead of gradients to build proposal mechanisms which can be employed for both differentiable and non-differentiable targets. These methods have been shown to…

统计计算 · 统计学 2024-06-21 Francesca R. Crucinio , Alain Durmus , Pablo Jiménez , Gareth O. Roberts

Sampling from a high-dimensional distribution is a fundamental task in statistics, engineering, and the sciences. A canonical approach is the Langevin Algorithm, i.e., the Markov chain for the discretized Langevin Diffusion. This is the…

统计理论 · 数学 2022-11-01 Jason M. Altschuler , Kunal Talwar

The preconditioned Metropolis adjusted Langevin algorithm (MALA) is a widely used method in statistical applications, where the choice of the preconditioning matrix plays a critical role. Recently, Titsias \cite{Titsias2024} demonstrated…

数值分析 · 数学 2025-03-13 Li-Li Wang , Guang-Hui Zheng

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…

机器学习 · 统计学 2018-01-26 Michalis K. Titsias , Omiros Papaspiliopoulos

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…

概率论 · 数学 2023-09-06 Alexander Christie , Yuanyuan Feng , Gautam Iyer , Alexei Novikov

Langevin Monte Carlo (LMC) is an iterative algorithm used to generate samples from a distribution that is known only up to a normalizing constant. The nonasymptotic dependence of its mixing time on the dimension and target accuracy is…

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…

统计理论 · 数学 2026-04-28 Youngwoo Kwon , Galin Jones , Qian Qin

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…

机器学习 · 计算机科学 2025-05-26 Adam D. Cobb , Susmit Jha