中文
相关论文

相关论文: Reflection coupling for unadjusted generalized Ham…

200 篇论文

Recently, a Wasserstein-type distance for Gaussian mixture models has been proposed. However, that framework can only be generalized to identifiable mixtures of general elliptically contoured distributions whose components come from the…

最优化与控制 · 数学 2025-03-19 Keyu Chen , Zetian Wang , Yunxin Zhang

We introduce a unified framework to estimate the convergence of Markov chains to equilibrium in Wasserstein distance. The framework can provide convergence bounds with rates ranging from polynomial to exponential, all derived from a…

概率论 · 数学 2025-06-09 Yanlin Qu , Jose Blanchet , Peter Glynn

Algorithms based on discretizing Langevin diffusion are popular tools for sampling from high-dimensional distributions. We develop novel connections between such Monte Carlo algorithms, the theory of Wasserstein gradient flow, and the…

统计计算 · 统计学 2019-05-13 Espen Bernton

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…

统计计算 · 统计学 2021-06-08 Zexi Song , Zhiqiang Tan

Stochastic gradient Hamiltonian Monte Carlo (SGHMC) is a variant of stochastic gradient with momentum where a controlled and properly scaled Gaussian noise is added to the stochastic gradients to steer the iterates towards a global minimum.…

最优化与控制 · 数学 2020-11-19 Xuefeng Gao , Mert Gürbüzbalaban , Lingjiong Zhu

Underdamped Langevin Monte Carlo (ULMC) is an algorithm used to sample from unnormalized densities by leveraging the momentum of a particle moving in a potential well. We provide a novel analysis of ULMC, motivated by two central questions:…

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…

概率论 · 数学 2023-01-20 Tim Johnston , Iosif Lytras , Sotirios Sabanis

We prove first-order convergence of semi-discrete monotone finite difference schemes for Hamilton--Jacobi equations on the Wasserstein space over a finite graph. A central challenge is the boundary degeneracy of the Wasserstein simplex,…

数值分析 · 数学 2026-05-22 Jianbo Cui , Tonghe Dang

Hamiltonian Monte Carlo (HMC) algorithms are among the most widely used sampling methods in high dimensional settings, yet their convergence properties are poorly understood in divergences that quantify relative density mismatch, such as…

机器学习 · 统计学 2026-01-15 Nawaf Bou-Rabee , Siddharth Mitra , Andre Wibisono

It is well known that nonlinear diffusion equations can be interpreted as a gradient flow in the space of probability measures equipped with the Euclidean Wasserstein distance. Under suitable convexity conditions on the nonlinearity, due to…

偏微分方程分析 · 数学 2014-02-13 François Bolley , José A. Carrillo

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

We prove a refined contraction inequality for diffusion semigroups with respect to the Wasserstein distance on a compact Riemannian manifold taking account of the dimension. The result generalizes in a Riemannian context, the dimensional…

概率论 · 数学 2014-12-16 Ivan Gentil

We establish a general framework to study the rate of convergence of a Euler type approximation scheme with decreasing time steps to the invariant measure, for a general class of stochastic systems. The error is measured in general…

概率论 · 数学 2026-03-03 Aurélien Alfonsi , Vlad Bally , Arturo Kohatsu-Higa

In this paper, we investigate a continuous time version of the Stochastic Langevin Monte Carlo method, introduced in [WT11], that incorporates a stochastic sampling step inside the traditional over-damped Langevin diffusion. This method is…

机器学习 · 统计学 2023-01-10 Marelys Crespo Navas , Sébastien Gadat , Xavier Gendre

In order to bring contraction analysis into the very fruitful and topical fields of stochastic and Bayesian systems, we extend here the theory describes in \cite{Lohmiller98} to random differential equations. We propose new definitions of…

最优化与控制 · 数学 2013-09-27 Nicolas Tabareau , Jean-Jacques Slotine

Hamiltonian Monte Carlo (HMC) is a Markov chain algorithm for sampling from a high-dimensional distribution with density $e^{-f(x)}$, given access to the gradient of $f$. A particular case of interest is that of a $d$-dimensional Gaussian…

机器学习 · 统计学 2022-09-27 Simon Apers , Sander Gribling , Dániel Szilágyi

The fact that a Markov diffusion semi-group on $\mathbb R^d$ contracts the $L^p$ Wasserstein distance, which has been extensively used to establish uniform-in-time stability estimates (e.g. with respect to numerical discretization errors),…

概率论 · 数学 2026-04-06 Pierre Monmarché

Contraction theory is a recently developed dynamic analysis and nonlinear control system design tool based on an exact differential analysis of convergence. This paper extends contraction theory to local and global stability analysis of…

数学物理 · 物理学 2007-05-23 Winfried Lohmiller , Jean-Jacques E. Slotine

Wasserstein distances are increasingly used in a wide variety of applications in machine learning. Sliced Wasserstein distances form an important subclass which may be estimated efficiently through one-dimensional sorting operations. In…

机器学习 · 统计学 2019-04-08 Mark Rowland , Jiri Hron , Yunhao Tang , Krzysztof Choromanski , Tamas Sarlos , Adrian Weller

We introduce Reflective Hamiltonian Monte Carlo (ReHMC), an HMC-based algorithm, to sample from a log-concave distribution restricted to a convex body. We prove that, starting from a warm start, the walk mixes to a log-concave target…

机器学习 · 计算机科学 2023-03-30 Apostolos Chalkis , Vissarion Fisikopoulos , Marios Papachristou , Elias Tsigaridas