English

Decentralized Langevin Dynamics

Optimization and Control 2020-09-22 v2 Information Theory math.IT

Abstract

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\epsilon-consensus for the continuous time stochastic differential equation, 2) convergence rate in L2L^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.

Keywords

Cite

@article{arxiv.2001.00665,
  title  = {Decentralized Langevin Dynamics},
  author = {Vyacheslav Kungurtsev},
  journal= {arXiv preprint arXiv:2001.00665},
  year   = {2020}
}
R2 v1 2026-06-23T13:01:53.473Z