Metrics
8 Record Views
Journal article
Decentralized Bayesian learning with Metropolis-adjusted Hamiltonian Monte Carlo
Machine learning, Vol.112(8), pp.2791-2819
08/2023
Web of Science ID: WOS:001015523900002
Abstract
Federated learning performed by a decentralized networks of agents is becoming increasingly important with the prevalence of embedded software on autonomous devices. Bayesian approaches to learning benefit from offering more information as to the uncertainty of a random quantity, and Langevin and Hamiltonian methods are effective at realizing sampling from an uncertain distribution with large parameter dimensions. Such methods have only recently appeared in the decentralized setting, and either exclusively use stochastic gradient Langevin and Hamiltonian Monte Carlo approaches that require a diminishing stepsize to asymptotically sample from the posterior and are known in practice to characterize uncertainty less faithfully than constant step-size methods with a Metropolis adjustment, or assume strong convexity properties of the potential function. We present the first approach to incorporating constant stepsize Metropolis-adjusted HMC in the decentralized sampling framework, show theoretical guarantees for consensus and probability distance to the posterior stationary distribution, and demonstrate their effectiveness numerically on standard real world problems, including decentralized learning of neural networks which is known to be highly non-convex.
Related links
Details
- Title
- Decentralized Bayesian learning with Metropolis-adjusted Hamiltonian Monte Carlo
- Publication Details
- Machine learning, Vol.112(8), pp.2791-2819
- Resource Type
- Journal article
- Publisher
- Springer US
- Number of pages
- 29
- Grant note
- W911NF-17-2-0196 / Army Research Laboratory (http://dx.doi.org/10.13039/100006754) Research Center for Informatics / OP VVV
- Copyright
- © 2023, The Author(s), under exclusive licence to Springer Science Business Media LLC, part of Springer Nature
- Identifiers
- WOS:001015523900002; 99381512427306600
- Academic Unit
- Intelligent Systems and Robotics; Hal Marcus College of Science and Engineering
- Language
- English