paper-with-me

홈 › Papers

Bayesian Federated Learning with Hamiltonian Monte Carlo: Algorithm and Theory

2024-07-09 · Jiajun Liang, Qian Zhang, Wei Deng, Qifan Song, Guang Lin

This work introduces a novel and efficient Bayesian federated learning algorithm, namely, the Federated Averaging stochastic Hamiltonian Monte Carlo (FA-HMC), for parameter estimation and uncertainty quantification. We establish rigorous convergence guarantees of FA-HMC on non-iid distributed data sets, under the strong convexity and Hessian smoothness assumptions. Our analysis investigates the effects of parameter space dimension, noise on gradients and momentum, and the frequency of communication (between the central node and local nodes) on the convergence and communication costs of FA-HMC. Beyond that, we establish the tightness of our analysis by showing that the convergence rate cannot be improved even for continuous FA-HMC process. Moreover, extensive empirical studies demonstrate that FA-HMC outperforms the existing Federated Averaging-Langevin Monte Carlo (FA-LD) algorithm.

📄 PDF Abstract BibTeX arXiv:2407.06935

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learningparameter estimationUncertainty Quantification

Similar Papers 제목 키워드 기반

Antithetic Riemannian Manifold And Quantum-Inspired Hamiltonian Monte Carlo

2021-07-05 · Wilson Tsakane Mongwe, Rendani Mbuvha, Tshilidzi Marwala

Markov Chain Monte Carlo inference of target posterior distributions in machine learning is predominately conducted via Hamiltonian Monte Carlo and its variants. This is due to Hamiltonian Monte Carlo based samplers abil…

Stochastic Gradient Hamiltonian Monte Carlo with Variance Reduction for Bayesian Inference

2018-03-29 · Zhize Li, Tianyi Zhang, Shuyu Cheng, Jun Zhu 외

Gradient-based Monte Carlo sampling algorithms, like Langevin dynamics and Hamiltonian Monte Carlo, are important methods for Bayesian inference. In large-scale settings, full-gradients are not affordable and thus stocha…

Bayesian Inference

Semi-Separable Hamiltonian Monte Carlo for Inference in Bayesian Hierarchical Models

2014-06-15 · NeurIPS 2014 12 · Yichuan Zhang, Charles Sutton

Sampling from hierarchical Bayesian models is often difficult for MCMC methods, because of the strong correlations between the model parameters and the hyperparameters. Recent Riemannian manifold Hamiltonian Monte Carlo …

Geometric Ergodicity in Modified Variations of Riemannian Manifold and Lagrangian Monte Carlo

2023-01-04 · James A. Brofos, Vivekananda Roy, Roy R. Lederman

Riemannian manifold Hamiltonian (RMHMC) and Lagrangian Monte Carlo (LMC) have emerged as powerful methods of Bayesian inference. Unlike Euclidean Hamiltonian Monte Carlo (EHMC) and the Metropolis-adjusted Langevin algori…

Bayesian Inference

Gradient-free Hamiltonian Monte Carlo with Efficient Kernel Exponential Families

2015-06-08 · NeurIPS 2015 12 · Heiko Strathmann, Dino Sejdinovic, Samuel Livingstone, Zoltan Szabo 외

We propose Kernel Hamiltonian Monte Carlo (KMC), a gradient-free adaptive MCMC algorithm based on Hamiltonian Monte Carlo (HMC). On target densities where classical HMC is not an option due to intractable gradients, KMC …

Bayesian Inference