Brian Jalaian
Brian Jalaian
Home
Posts
Projects
Talks
Publications
Contact
Light
Dark
Automatic
Uncertainty Quantification
Decentralized Bayesian Learning with Metropolis-Adjusted Hamiltonian Monte Carlo
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.
Vyacheslav Kungurtsev
,
Adam Cobb
,
Tara Javidi
,
Brian Jalaian
PDF
Cite
Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting
Hamiltonian Monte Carlo (HMC) is a Markov chain Monte Carlo (MCMC) approach that exhibits favourable exploration properties in …
Adam D. Cobb
,
Brian Jalaian
PDF
Cite
Maximize Spectrum Efficiency in Underlay Coexistence With Channel Uncertainty
We consider an underlay coexistence scenario where secondary users (SUs) must keep their interference to the primary users (PUs) under …
Shaoran Li
,
Yan Huang
,
Chengzhang Li
,
Brian Jalaian
,
Y. Thomas Hou
,
Wenjing Lou
,
Stephen Russell
PDF
Cite
DOI
Cite
×