中文
相关论文

相关论文: Fast Convergence of Langevin Dynamics on Manifold:…

200 篇论文

The stochastic gradient Langevin Dynamics is one of the most fundamental algorithms to solve sampling problems and non-convex optimization appearing in several machine learning applications. Especially, its variance reduced versions have…

机器学习 · 计算机科学 2022-11-22 Yuri Kinoshita , Taiji Suzuki

We study the Riemannian Langevin Algorithm for the problem of sampling from a distribution with density $\nu$ with respect to the natural measure on a manifold with metric $g$. We assume that the target density satisfies a log-Sobolev…

机器学习 · 计算机科学 2022-04-25 Khashayar Gatmiry , Santosh S. Vempala

Sampling from constrained statistical distributions is a fundamental task in various fields including Bayesian statistics, computational chemistry, and statistical physics. This article considers the cases where the constrained distribution…

机器学习 · 计算机科学 2025-10-28 Kijung Jeon , Michael Muehlebach , Molei Tao

We study the problem of learning multi-index models in high-dimensions using a two-layer neural network trained with the mean-field Langevin algorithm. Under mild distributional assumptions on the data, we characterize the effective…

机器学习 · 统计学 2025-03-28 Alireza Mousavi-Hosseini , Denny Wu , Murat A. Erdogdu

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…

机器学习 · 统计学 2021-01-12 Anjaly Parayil , He Bai , Jemin George , Prudhvi Gurram

Langevin diffusion is a commonly used tool for sampling from a given distribution. In this work, we establish that when the target density $p^*$ is such that $\log p^*$ is $L$ smooth and $m$ strongly convex, discrete Langevin diffusion…

机器学习 · 统计学 2017-11-02 Xiang Cheng , Peter Bartlett

Sampling from distributions play a crucial role in aiding practitioners with statistical inference. However, in numerous situations, obtaining exact samples from complex distributions is infeasible. Consequently, researchers often turn to…

统计计算 · 统计学 2024-04-01 Riddhiman Bhattacharya , Tiefeng Jiang

Understanding the dimension dependency of computational complexity in high-dimensional sampling problem is a fundamental problem, both from a practical and theoretical perspective. Compared with samplers with unbiased stationary…

机器学习 · 计算机科学 2024-03-12 Xunpeng Huang , Hanze Dong , Difan Zou , Tong Zhang

We provide a new convergence analysis of stochastic gradient Langevin dynamics (SGLD) for sampling from a class of distributions that can be non-log-concave. At the core of our approach is a novel conductance analysis of SGLD using an…

机器学习 · 计算机科学 2021-02-24 Difan Zou , Pan Xu , Quanquan Gu

This work explores a novel perspective on solving nonconvex and nonsmooth optimization problems by leveraging sampling based methods. Instead of treating the objective function purely through traditional (often deterministic) optimization…

最优化与控制 · 数学 2025-05-21 Nahom Seyoum , Haoxiang You

The Langevin Markov chain algorithms are widely deployed methods to sample from distributions in challenging high-dimensional and non-convex statistics and machine learning applications. Despite this, current bounds for the Langevin…

数据结构与算法 · 计算机科学 2019-04-10 Oren Mangoubi , Nisheeth K. Vishnoi

Recently, the task of image generation has attracted much attention. In particular, the recent empirical successes of the Markov Chain Monte Carlo (MCMC) technique of Langevin Dynamics have prompted a number of theoretical advances; despite…

机器学习 · 统计学 2020-06-24 Adam Block , Youssef Mroueh , Alexander Rakhlin , Jerret Ross

Langevin algorithms are gradient descent methods with additive noise. They have been used for decades in Markov chain Monte Carlo (MCMC) sampling, optimization, and learning. Their convergence properties for unconstrained non-convex…

机器学习 · 计算机科学 2020-12-23 Andrew Lamperski

We study the Unadjusted Langevin Algorithm (ULA) for sampling from a probability distribution $\nu = e^{-f}$ on $\mathbb{R}^n$. We prove a convergence guarantee in Kullback-Leibler (KL) divergence assuming $\nu$ satisfies a log-Sobolev…

数据结构与算法 · 计算机科学 2022-03-04 Santosh S. Vempala , Andre Wibisono

The mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex functional on the Wasserstein space over $\mathbb{R}^d$, and has gained attention recently as a model for the gradient descent dynamics of interacting…

机器学习 · 计算机科学 2026-05-19 Anming Gu , Juno Kim

Given a convex function $f\colon\mathbb{R}^{d}\to\mathbb{R}$, the problem of sampling from a distribution $\propto e^{-f(x)}$ is called log-concave sampling. This task has wide applications in machine learning, physics, statistics, etc. In…

量子物理 · 物理学 2023-12-11 Andrew M. Childs , Tongyang Li , Jin-Peng Liu , Chunhao Wang , Ruizhe Zhang

Federated learning uses a set of techniques to efficiently distribute the training of a machine learning algorithm across several devices, who own the training data. These techniques critically rely on reducing the communication cost -- the…

机器学习 · 计算机科学 2022-06-08 Lukang Sun , Adil Salim , Peter Richtárik

We consider the problem of sampling from a target distribution, which is \emph {not necessarily logconcave}, in the context of empirical risk minimization and stochastic optimization as presented in Raginsky et al. (2017). Non-asymptotic…

统计理论 · 数学 2021-02-03 Ngoc Huy Chau , Éric Moulines , Miklos Rásonyi , Sotirios Sabanis , Ying Zhang

We propose a federated averaging Langevin algorithm (FA-LD) for uncertainty quantification and mean predictions with distributed clients. In particular, we generalize beyond normal posterior distributions and consider a general class of…

机器学习 · 统计学 2023-10-06 Wei Deng , Qian Zhang , Yi-An Ma , Zhao Song , Guang Lin

The technique of modifying the geometry of a problem from Euclidean to Hessian metric has proved to be quite effective in optimization, and has been the subject of study for sampling. The Mirror Langevin Diffusion (MLD) is a sampling…

数据结构与算法 · 计算机科学 2021-10-12 Ruilin Li , Molei Tao , Santosh S. Vempala , Andre Wibisono
‹ 上一页 1 2 3 10 下一页 ›