mlsanityData to 13 Oct 2026

Asynchronous Bayesian Learning over a Network

arXiv 2211.08603 ↗First posted 16 Nov 2022cs.LG cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

We present a practical asynchronous data fusion model for networked agents to perform distributed Bayesian learning without sharing raw data. Our algorithm uses a gossip-based approach where pairs of randomly selected agents employ unadjusted Langevin dynamics for parameter sampling. We also introduce an event-triggered mechanism to further reduce communication between gossiping agents. These mechanisms drastically reduce communication overhead and help avoid bottlenecks commonly experienced with distributed algorithms. In addition, the reduced link utilization by the algorithm is expected to increase resiliency to occasional link failure. We establish mathematical guarantees for our algorithm and demonstrate its effectiveness via numerical experiments.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 19 of its 27 references that are in the map. First posted on arXiv 16 Nov 2022.

Builds on

19 of 27 references.

References · 19

  1. 2017Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysiscited by 242
  2. 2014Theoretical guarantees for approximate sampling from smooth and log-concave densitiescited by 207
  3. 2015Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithmcited by 195
  4. 2016High-dimensional Bayesian inference via the Unadjusted Langevin Algorithmcited by 145
  5. 2017Underdamped Langevin MCMC: A non-asymptotic analysiscited by 132
  6. 2018Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problemcited by 123
  7. 2017Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimizationcited by 97
  8. 2017Convergence of Langevin MCMC in KL-divergencecited by 87
  9. 2018Sampling Can Be Faster Than Optimizationcited by 68
  10. 2018Sharp convergence rates for Langevin dynamics in the nonconvex settingcited by 67
  11. 2019Improved Bounds for Discretization of Langevin Diffusions: Near-Optimal Rates without Convexitycited by 38
  12. 2019Nonasymptotic estimates for Stochastic Gradient Langevin Dynamics under local conditions in nonconvex optimizationcited by 38
7 more
  1. 2018Non-asymptotic bounds for sampling algorithms without log-concavitycited by 35
  2. 2020Decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlocited by 19
  3. 2020Federated Stochastic Gradient Langevin Dynamicscited by 16
  4. 2019On stochastic gradient Langevin dynamics with dependent data streams: the fully non-convex casecited by 14
  5. 2020Bayesian Federated Learning over Wireless Networkscited by 8
  6. 2021Decentralized Bayesian Learning with Metropolis-Adjusted Hamiltonian Monte Carlocited by 4
  7. 2021Decentralized Langevin Dynamics over a Directed Graphcited by 3

Built on by

Not cited yet.