Distributed event-triggered unadjusted Langevin algorithm for Bayesian learning

DOI10.1016/J.AUTOMATICA.2023.111221zbMATH Open1520.93306MaRDI QIDQ6136164FDOQ6136164

Authors: Kinjal Bhar, He Bai, Jemin George, Carl Busart 

Publication date: 28 August 2023

Published in: Automatica (Search for Journal in Brave)

Recommendations

• Distributed Bayesian learning with stochastic natural gradient expectation propagation and the posterior server
• Distributed Bayesian machine learning procedures
• Decentralized Bayesian learning with Metropolis-adjusted Hamiltonian Monte Carlo
• Distributed Variational Bayesian Algorithms Over Sensor Networks
• Hybrid deterministic-stochastic gradient Langevin dynamics for Bayesian learning
• scientific article; zbMATH DE number 7365721
• Fast Convergence Rates for Distributed Non-Bayesian Learning
• Stochastic Event-triggered Variational Bayesian Filtering

zbMATH Keywords

Bayesian learningLangevin dynamicsevent-triggered communicationdistributed multi-agent networks

Mathematics Subject Classification ID

Discrete event control/observation systems (93C65) Multi-agent systems (93A16) Networked control (93B70)

Cites Work

• Exponential convergence of Langevin distributions and their discrete approximations
• The Variational Formulation of the Fokker--Planck Equation
• Distributed Event-Triggered Control for Multi-Agent Systems
• Logarithmic Sobolev Inequalities
• Generalized inverse of the Laplacian matrix and some applications
• Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
• Simulating Hamiltonian Dynamics
• Dynamic Triggering Mechanisms for Event-Triggered Control
• An introduction to MCMC for machine learning
• Distributed convex optimization via continuous-time coordination algorithms with discrete-time communication
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• Distributed linear parameter estimation: asymptotically efficient adaptive strategies
• Sampling can be faster than optimization
• Nonasymptotic bounds for sampling algorithms without log-concavity
• Convergence of Langevin MCMC in KL-divergence
• Variance-Reduced Decentralized Stochastic Optimization With Accelerated Convergence
• On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case
• Improved bounds for discretization of Langevin diffusions: near-optimal rates without convexity
• Title not available (Why is that?)
• Nonasymptotic estimates for stochastic gradient Langevin dynamics under local conditions in nonconvex optimization
• SPARQ-SGD: Event-Triggered and Compressed Communication in Decentralized Optimization

Cited In (4)

• Decentralized fused-learner architectures for Bayesian reinforcement learning
• Event-triggered learning
• Stochastic Event-triggered Variational Bayesian Filtering
• Decentralized Bayesian learning with Metropolis-adjusted Hamiltonian Monte Carlo

This page was built for publication: Distributed event-triggered unadjusted Langevin algorithm for Bayesian learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6136164)