首页/论文/2001.00665

arXiv 2001.006652020-01math.OCcs.ITmath.IT

Decentralized Langevin Dynamics

Vyacheslav Kungurtsev

英文摘要：

Langevin MCMC gradient optimization is a class of increasingly popular methods for estimating a posterior distribution. This paper addresses the algorithm as applied in a decentralized setting, wherein data is distributed across a network of agents which act to cooperatively solve the problem using peer-to-peer gossip communication. We show, theoretically, results in 1) the time-complexity to $ε$-consensus for the continuous time stochastic differential equation, 2) convergence rate in $L^2$ norm to consensus for the discrete implementation as defined by the Euler-Maruyama discretization and 3) convergence rate in the Wasserstein metric to the optimal stationary distribution for the discretized dynamics.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Decentralized Langevin Dynamics over a Directed Graph

The prevalence of technologies in the space of the Internet of Things and use of multi-processing computing platforms to aid in the computation required to perform learning and inference from large volumes of data has necessitated the extensive study of algorithms on decentralized platforms. In these settings, computing nodes send and receive data across graph-structured communication links, and using a combination of local computation and consensus-seeking communication, cooperately solve a problem of interest. Recently, Langevin dynamics as a tool for high dimensional sampling and posterior …

2021-03-06cs.DCmath.OCmath.PR

Decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo

Rutgers Business School（罗格斯大学商学院）；The Chinese University of Hong Kong（香港中文大学）；Florida State University（佛罗里达州立大学）

Stochastic gradient Langevin dynamics (SGLD) and stochastic gradient Hamiltonian Monte Carlo (SGHMC) are two popular Markov Chain Monte Carlo (MCMC) algorithms for Bayesian inference that can scale to large datasets, allowing to sample from the posterior distribution of the parameters of a statistical model given the input data and the prior distribution over the model parameters. However, these algorithms do not apply to the decentralized learning setting, when a network of agents are working collaboratively to learn the parameters of a statistical model without sharing their individual data …

2021-08-26cs.LGmath.OCstat.ML

DIGing--SGLD：时变网络上的去中心化可扩展朗之万采样

DIGing--SGLD: Decentralized and Scalable Langevin Sampling over Time--Varying Networks

本文提出DIGing-SGLD算法，解决时变网络下现有去中心化SGLD的静态拓扑限制与采样偏差问题，首次提供有限时间非渐近Wasserstein收敛保证，经实验验证其性能优异。

2026-08-25cs.LGmath.OCstat.ML

广义EXTRA随机梯度Langevin动力学

Generalized EXTRA stochastic gradient Langevin dynamics

针对去中心化SGLD算法在智能体网络中引入偏差的问题，提出广义EXTRA随机梯度Langevin动力学，在全批量下消除偏差，小批量下性能界限更优。

2025-10-26cs.LGmath.OC

Decentralized Bayesian Learning with Metropolis-Adjusted Hamiltonian Monte Carlo

Czech Technical University in Prague（捷克布拉格技术大学）；SRI International（SRI国际公司）；University of California, San Diego（加州大学圣地亚哥分校）；DEVCOM Army Research Laboratory（美国陆军DEVCOM研究实验室）

Federated learning performed by a decentralized networks of agents is becoming increasingly important with the prevalence of embedded software on autonomous devices. Bayesian approaches to learning benefit from offering more information as to the uncertainty of a random quantity, and Langevin and Hamiltonian methods are effective at realizing sampling from an uncertain distribution with large parameter dimensions. Such methods have only recently appeared in the decentralized setting, and either exclusively use stochastic gradient Langevin and Hamiltonian Monte Carlo approaches that require a d…

2021-07-15cs.LGmath.OCstat.ML

Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problem

Department of Electrical & Computer Engineering University of Wisconsin – Madison（威斯康星大学麦迪逊分校电气与计算机工程系）

We study sampling as optimization in the space of measures. We focus on gradient flow-based optimization with the Langevin dynamics as a case study. We investigate the source of the bias of the unadjusted Langevin algorithm (ULA) in discrete time, and consider how to remove or reduce the bias. We point out the difficulty is that the heat flow is exactly solvable, but neither its forward nor backward method is implementable in general, except for Gaussian data. We propose the symmetrized Langevin algorithm (SLA), which should have a smaller bias than ULA, at the price of implementing a proximal…

2018-06-06cs.ITcs.LGmath.IT

更多相关论文收起更多论文

Approximation to stochastic variance reduced gradient Langevin dynamics by stochastic delay differential equations

We study in this paper a weak approximation to stochastic variance reduced gradient Langevin dynamics by stochastic delay differential equations in Wasserstein-1 distance, and obtain a uniform error bound. Our approach is via a refined Lindeberg principle and Malliavin calculus.

2021-12-19math.OCmath.PR

Mean-Field Langevin Dynamics: Exponential Convergence and Annealing

Noisy particle gradient descent (NPGD) is an algorithm to minimize convex functions over the space of measures that include an entropy term. In the many-particle limit, this algorithm is described by a Mean-Field Langevin dynamics - a generalization of the Langevin dynamics with a non-linear drift - which is our main object of study. Previous work have shown its convergence to the unique minimizer via non-quantitative arguments. We prove that this dynamics converges at an exponential rate, under the assumption that a certain family of Log-Sobolev inequalities holds. This assumption holds for i…

2022-08-11math.OC

Non-Convex Optimization via Non-Reversible Stochastic Gradient Langevin Dynamics

Stochastic Gradient Langevin Dynamics (SGLD) is a powerful algorithm for optimizing a non-convex objective, where a controlled and properly scaled Gaussian noise is added to the stochastic gradients to steer the iterates towards a global minimum. SGLD is based on the overdamped Langevin diffusion which is reversible in time. By adding an anti-symmetric matrix to the drift term of the overdamped Langevin diffusion, one gets a non-reversible diffusion that converges to the same stationary distribution with a faster convergence rate. In this paper, we study the non reversible Stochastic Gradient …

2020-06-02math.OCstat.ML

Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization

UCLA（加州大学洛杉矶分校）；University of Virginia（弗吉尼亚大学）

We present a unified framework to analyze the global convergence of Langevin dynamics based algorithms for nonconvex finite-sum optimization with $n$ component functions. At the core of our analysis is a direct analysis of the ergodicity of the numerical approximations to Langevin dynamics, which leads to faster convergence rates. Specifically, we show that gradient Langevin dynamics (GLD) and stochastic gradient Langevin dynamics (SGLD) converge to the almost minimizer within $\tilde O\big(nd/(λε) \big)$ and $\tilde O\big(d^7/(λ^5ε^5) \big)$ stochastic gradient evaluations respectively, where…

2020-10-19cs.LGmath.OCstat.ML

Convergence of Simulated Annealing Using Kinetic Langevin Dynamics

We study the simulated annealing algorithm based on the kinetic Langevin dynamics, in order to find the global minimum of a non-convex potential function. For both the continuous time formulation and a discrete time analogue, we obtain the convergence rate results under technical conditions on the potential function, together with an appropriate choice of the cooling schedule and the time discretization parameters.

2022-06-13cs.NAmath.NAmath.OC

带方差缩减的随机梯度朗之万动力学

Stochastic Gradient Langevin Dynamics with Variance Reduction

Michigan State University（密歇根州立大学）；University of Colorado Boulder（科罗拉多大学博尔德分校）

本文研究带方差缩减的随机梯度朗之万动力学，证明其对非凸目标局部极小值的改进收敛性及遍历性，揭示其寻找全局极小值的潜力。

2021-02-12cs.LGmath.OC

Non-asymptotic estimation of risk measures using stochastic gradient Langevin dynamics

In this paper we will study the approximation of arbitrary law invariant risk measures. As a starting point, we approximate the average value at risk using stochastic gradient Langevin dynamics, which can be seen as a variant of the stochastic gradient descent algorithm. Further, the Kusuoka's spectral representation allows us to bootstrap the estimation of the average value at risk to extend the algorithm to general law invariant risk measures. We will present both theoretical, non-asymptotic convergence rates of the approximation algorithm and numerical simulations.

2023-02-10math.OCq-fin.MFq-fin.RM

随机梯度朗之万动力学的泛函中心极限定理和强大数定律

Functional Central Limit Theorem and Strong Law of Large Numbers for Stochastic Gradient Langevin Dynamics

本文研究了固定步长SGLD在非独立数据流下的混合性质，将其建模为随机环境中的马尔可夫链，并为其推导了强大数定律和泛函中心极限定理。

2023-07-29cs.LGmath.OCmath.PR

面向分布极小极大问题的对称平均场Langevin动力学

Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems

本文首次将平均场Langevin动力学扩展至概率分布上的极小极大优化，提出单循环算法MFL-AG和双循环算法MFL-ABR，分别建立对混合Nash均衡的平均迭代收敛性和线性最后迭代收敛性，并证明时间一致混沌传播结果，应用于零和Markov博弈。

2024-02-16math.OCstat.ML

平均场欠阻尼朗之万动力学及其时空离散化

Mean-field underdamped Langevin dynamics and its spacetime discretization

提出N粒子欠阻尼朗之万算法，通过平均场欠阻尼动力学的时空离散化，优化概率测度上的非线性泛函，并证明其全局收敛与快速混合。

2024-02-06math.OCmath.STstat.CO

面向非凸约束问题全局优化的反射梯度朗之万动力学收敛误差分析

Convergence Error Analysis of Reflected Gradient Langevin Dynamics for Globally Optimizing Non-Convex Constrained Problems

本研究将梯度朗之万动力学相关框架拓展至非凸可行域上的非凸优化问题，提出基于反射梯度朗之万动力学的全局优化算法，结合边界反射与诺伊曼边界泊松方程概率表示，得到优于现有凸约束非凸问题方法的收敛速率。

2024-08-13math.OCmath.PRstat.ML