Thinned Mean Field Langevin Dynamics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Zonghao, Kanagawa, Heishiro, Briol, François-Xavier, Oates, Chris J., Mackey, Lester
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911725078446080
author Chen, Zonghao
Kanagawa, Heishiro
Briol, François-Xavier
Oates, Chris J.
Mackey, Lester
author_facet Chen, Zonghao
Kanagawa, Heishiro
Briol, François-Xavier
Oates, Chris J.
Mackey, Lester
contents Several important learning tasks can be formulated as minimizing an entropy-regularized objective over an appropriate space of probability distributions. Mean-field Langevin dynamics (MFLD) facilitate computation in this general context, casting the minimizer as the invariant distribution of a McKean--Vlasov process, which can be numerically discretized using $N$ particles and thus simulated. However, simulating this interacting particle system has computational complexity of order $N^2$. Motivated by recent research into \emph{kernel thinning}, we propose \texttt{KT-MFLD}, in which each particle interacts only with a thinned particle coreset of size $\mathcal{O}(N^{\frac{1}{2}})$. \texttt{KT-MFLD} thus reduces the computational complexity to order $N^{\frac{3}{2}}$ while, under mild regularity conditions, achieving the same convergence guarantees (up to logarithmic factors) as MFLD. Our theoretical analysis is empirically confirmed on tasks including the training of student-teacher neural networks, quantization with maximum mean discrepancy, and computation of predictively-oriented posteriors in a post-Bayesian framework.
format Preprint
id arxiv_https___arxiv_org_abs_2605_28589
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Thinned Mean Field Langevin Dynamics
Chen, Zonghao
Kanagawa, Heishiro
Briol, François-Xavier
Oates, Chris J.
Mackey, Lester
Machine Learning
Several important learning tasks can be formulated as minimizing an entropy-regularized objective over an appropriate space of probability distributions. Mean-field Langevin dynamics (MFLD) facilitate computation in this general context, casting the minimizer as the invariant distribution of a McKean--Vlasov process, which can be numerically discretized using $N$ particles and thus simulated. However, simulating this interacting particle system has computational complexity of order $N^2$. Motivated by recent research into \emph{kernel thinning}, we propose \texttt{KT-MFLD}, in which each particle interacts only with a thinned particle coreset of size $\mathcal{O}(N^{\frac{1}{2}})$. \texttt{KT-MFLD} thus reduces the computational complexity to order $N^{\frac{3}{2}}$ while, under mild regularity conditions, achieving the same convergence guarantees (up to logarithmic factors) as MFLD. Our theoretical analysis is empirically confirmed on tasks including the training of student-teacher neural networks, quantization with maximum mean discrepancy, and computation of predictively-oriented posteriors in a post-Bayesian framework.
title Thinned Mean Field Langevin Dynamics
topic Machine Learning
url https://arxiv.org/abs/2605.28589