中文
相关论文

相关论文: Non-asymptotic analysis of Langevin-type Monte Car…

200 篇论文

In recent papers it has been demonstrated that sampling a Gibbs distribution from an appropriate time-irreversible Langevin process is, from several points of view, advantageous when compared to sampling from a time-reversible one. Adding…

概率论 · 数学 2015-02-20 Luc Rey-Bellet , Konstantinos Spiliopoulos

We propose a new discretization of the mirror-Langevin diffusion and give a crisp proof of its convergence. Our analysis uses relative convexity/smoothness and self-concordance, ideas which originated in convex optimization, together with a…

统计理论 · 数学 2021-10-26 Kwangjun Ahn , Sinho Chewi

The classical Langevin Monte Carlo method looks for samples from a target distribution by descending the samples along the gradient of the target distribution. The method enjoys a fast convergence rate. However, the numerical cost is…

机器学习 · 统计学 2025-03-07 Zhiyan Ding , Qin Li

We provide full theoretical guarantees for the convergence behaviour of diffusion-based generative models under the assumption of strongly log-concave data distributions while our approximating class of functions used for score estimation…

机器学习 · 计算机科学 2025-02-18 Stefano Bruno , Ying Zhang , Dong-Young Lim , Ömer Deniz Akyildiz , Sotirios Sabanis

We investigate a weighted Multilevel Richardson-Romberg extrapolation for the ergodic approximation of invariant distributions of diffusions adapted from the one introduced in~[Lemaire-Pag\`es, 2013] for regular Monte Carlo simulation. In a…

概率论 · 数学 2016-07-05 Gilles Pagès , Fabien Panloup

An Euler discretization of the Langevin diffusion is known to converge to the global minimizers of certain convex and non-convex optimization problems. We show that this property holds for any suitably smooth diffusion and that different…

机器学习 · 统计学 2019-12-30 Murat A. Erdogdu , Lester Mackey , Ohad Shamir

In this paper, we study a method to sample from a target distribution $\pi$ over $\mathbb{R}^d$ having a positive density with respect to the Lebesgue measure, known up to a normalisation factor. This method is based on the Euler…

统计理论 · 数学 2016-12-20 Alain Durmus , Eric Moulines

This paper proposes a novel Bayesian framework for solving Poisson inverse problems by devising a Monte Carlo sampling algorithm which accounts for the underlying non-Euclidean geometry. To address the challenges posed by the Poisson…

统计计算 · 统计学 2025-11-18 Elhadji Cisse Faye , Mame Diarra Fall , Nicolas Dobigeon , Eric Barat

We propose a scalable inference algorithm for Bayes posteriors defined on a reproducing kernel Hilbert space (RKHS). Given a likelihood function and a Gaussian random element representing the prior, the corresponding Bayes posterior measure…

机器学习 · 统计学 2025-02-26 Veit Wild , James Wu , Dino Sejdinovic , Jeremias Knoblauch

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

We formulate gradient-based Markov chain Monte Carlo (MCMC) sampling as optimization on the space of probability measures, with Kullback-Leibler (KL) divergence as the objective functional. We show that an underdamped form of the Langevin…

In this work, we propose a first-order sampling method called the Metropolis-adjusted Preconditioned Langevin Algorithm for approximate sampling from a target distribution whose support is a proper convex subset of $\mathbb{R}^{d}$. Our…

统计计算 · 统计学 2025-02-27 Vishwak Srinivasan , Andre Wibisono , Ashia Wilson

In this paper, we propose two new algorithms, namely, aHOLA and aHOLLA, to sample from high-dimensional target distributions with possibly super-linearly growing potentials. We establish non-asymptotic convergence bounds for aHOLA in…

统计理论 · 数学 2025-08-11 Ariel Neufeld , Ying Zhang

This paper is concerned with sampling from probability distributions $\pi$ on $\mathbb{R}^d$ admitting a density of the form $\pi(x) \propto e^{-U(x)}$, where $U(x)=F(x)+G(Kx)$ with $K$ being a linear operator and $G$ being…

最优化与控制 · 数学 2024-05-28 Andreas Habring , Martin Holler , Thomas Pock

The particle Gibbs sampler is a Markov chain Monte Carlo (MCMC) algorithm to sample from the full posterior distribution of a state-space model. It does so by executing Gibbs sampling steps on an extended target distribution defined on the…

统计计算 · 统计学 2015-07-29 Nicolas Chopin , Sumeetpal S. Singh

We study the problem of sampling from a distribution $p^*(x) \propto \exp\left(-U(x)\right)$, where the function $U$ is $L$-smooth everywhere and $m$-strongly convex outside a ball of radius $R$, but potentially nonconvex inside this ball.…

We develop a novel class of MCMC algorithms based on a stochastized Nesterov scheme. With an appropriate addition of noise, the result is a time-inhomogeneous underdamped Langevin equation, which we prove emits a specified target…

计算工程、金融与科学 · 计算机科学 2023-11-29 Duy H. Thai , Alexander L. Young , David B. Dunson

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:…

A new approach in stochastic optimization via the use of stochastic gradient Langevin dynamics (SGLD) algorithms, which is a variant of stochastic gradient decent (SGD) methods, allows us to efficiently approximate global minimizers of…

投资组合管理 · 定量金融 2020-07-06 Sotirios Sabanis , Ying Zhang

We propose a novel kinetic Langevin sampler based on a specific splitting scheme using the exact harmonic Langevin integrator. For strongly log-concave target measures, the sampler exploits a decomposition of the strongly convex potential…

统计计算 · 统计学 2026-05-26 Katharina Schuh