Bayesian Federated Learning with Hamiltonian Monte Carlo: Algorithm and Theory

DOI10.1080/10618600.2024.2380051MaRDI QIDQ6968060zbMATH OpenFDO

Authors Jiajun Liang, Wei Deng, Qifan Song, Guang Lin

Publication date 25 June 2025

Published in Journal of Computational and Graphical Statistics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/10618600.2024.2380051

Mathematics Subject Classification ID

Statistics (62-XX)

Cites work

• Fast mixing of Metropolized Hamiltonian Monte Carlo: benefits of multi-step gradients
• scientific article; zbMATH DE number 7626754 (Why is no real title available?)
• MCMC using Hamiltonian dynamics
• Optimal convergence rate of Hamiltonian Monte Carlo for strongly logconcave distributions
• Riemann manifold Langevin and Hamiltonian Monte Carlo methods. With discussion and authors' reply
• Stochastic gradient Hamiltonian Monte Carlo for non-convex learning
• Stochastic gradient Markov chain Monte Carlo
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
• Variational Bayesian Inference for Parametric and Nonparametric Regression With Missing Data

Cited in

(1)

• Federated learning: examining statistical operating characteristics in the context of privacy-preserving information sharing

This page was built for publication: Bayesian Federated Learning with Hamiltonian Monte Carlo: Algorithm and Theory

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6968060)