Decentralized Bayesian learning with Metropolis-adjusted Hamiltonian Monte Carlo

DOI10.1007/S10994-023-06345-6MaRDI QIDQ6134345zbMATH OpenOpenAlexFDO

Authors Vyacheslav Kungurtsev, Adam D. Cobb, Tara Javidi, Brian A. Jalaian

Publication date 22 August 2023

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2107.07211

zbMATH Keywords

Monte CarloHMCfederated learningdecentralized learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

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.

Recommendations

• Distributed event-triggered unadjusted Langevin algorithm for Bayesian learning
• Decentralized fused-learner architectures for Bayesian reinforcement learning
• Hybrid deterministic-stochastic gradient Langevin dynamics for Bayesian learning
• Distributed cooperative Bayesian learning strategies.
• Hamiltonian Markov chain Monte Carlo for partitioned sample spaces with application to Bayesian deep neural nets

Cites work

• scientific article; zbMATH DE number 7626754 (Why is no real title available?)
• Balancing Communication and Computation in Distributed Optimization
• Consistency and fluctuations for stochastic gradient Langevin dynamics
• Coupling and convergence for Hamiltonian Monte Carlo
• Distributed stochastic gradient tracking methods
• Exponential convergence of Langevin distributions and their discrete approximations
• Global convergence of stochastic gradient Hamiltonian Monte Carlo for nonconvex stochastic optimization: nonasymptotic performance bounds and momentum-based acceleration
• Hedonic housing prices and the demand for clean air
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• On stationary-point hitting time and ergodicity of stochastic gradient Langevin dynamics
• Stochastic gradient Hamiltonian Monte Carlo for non-convex learning

Cited in

(2)

• Distributed event-triggered unadjusted Langevin algorithm for Bayesian learning
• Decentralized fused-learner architectures for Bayesian reinforcement learning

This page was built for publication: Decentralized Bayesian learning with Metropolis-adjusted Hamiltonian Monte Carlo

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6134345)