paper-with-me

홈 › Papers

Mean-field underdamped Langevin dynamics and its spacetime discretization

2023-12-26 · Qiang Fu, Ashia Wilson

We propose a new method called the N-particle underdamped Langevin algorithm for optimizing a special class of non-linear functionals defined over the space of probability measures. Examples of problems with this formulation include training mean-field neural networks, maximum mean discrepancy minimization and kernel Stein discrepancy minimization. Our algorithm is based on a novel spacetime discretization of the mean-field underdamped Langevin dynamics, for which we provide a new, fast mixing guarantee. In addition, we demonstrate that our algorithm converges globally in total variation distance, bridging the theoretical gap between the dynamics and its practical implementation.

📄 PDF Abstract BibTeX arXiv:2312.16360

Code (1)

qiangfu09/nula 공식 구현 pytorch

Tasks

Density Estimation

Similar Papers 제목 키워드 기반

Ergodicity of the underdamped mean-field Langevin dynamics

2020-07-29 · Anna Kazeykina, Zhenjie Ren, Xiaolu Tan, Junjian Yang

We study the long time behavior of an underdamped mean-field Langevin (MFL) equation, and provide a general convergence as well as an exponential convergence rate result under different conditions. The results on the MFL…

Learning Relationship between Quantum Walks and Underdamped Langevin Dynamics

2026-01-04 · Yazhen Wang arxiv

Fast computational algorithms are in constant demand, and their development has been driven by advances such as quantum speedup and classical acceleration. This paper intends to study search algorithms based on quantum w…

Fisher information dissipation for time inhomogeneous stochastic differential equations

2024-02-01 · Qi Feng, Xinzhe Zuo, Wuchen Li

We provide a Lyapunov convergence analysis for time-inhomogeneous variable coefficient stochastic differential equations (SDEs). Three typical examples include overdamped, irreversible drift, and underdamped Langevin dyn…

Unbiased Estimation using Underdamped Langevin Dynamics

2022-06-14 · Hamza Ruzayqat, Neil K. Chada, Ajay Jasra

In this work we consider the unbiased estimation of expectations w.r.t.~probability measures that have non-negative Lebesgue density, and which are known point-wise up-to a normalizing constant. We focus upon developing …

Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence

2026-03-02 · Shiyuan Zhang, Qiwei Di, Xuheng Li, Quanquan Gu arxiv

Underdamped Langevin dynamics (ULD) is a widely-used sampler for Gibbs distributions $π\propto e^{-V}$, and is often empirically effective in high dimensions. However, existing non-asymptotic convergence guarantees for d…