Fast Convergence Rates for Distributed Non-Bayesian Learning

DOI10.1109/TAC.2017.2690401MaRDI QIDQ4566974zbMATH OpenOpenAlexFDO

Authors Angelia Nedić, Alex Olshevsky, César A. Uribe

Publication date 27 June 2018

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1508.05161

Mathematics Subject Classification ID

Bayesian inference (62F15) Estimation in multivariate analysis (62H12) Distributed algorithms (68W15) Stochastic learning and adaptive control (93E35)

Abstract: We consider the problem of distributed learning, where a network of agents collectively aim to agree on a hypothesis that best explains a set of distributed observations of conditionally independent random processes. We propose a distributed algorithm and establish consistency, as well as a non-asymptotic, explicit and geometric convergence rate for the concentration of the beliefs around the set of optimal hypotheses. Additionally, if the agents interact over static networks, we provide an improved learning protocol with better scalability with respect to the number of nodes in the network.

Cited in

(20)

• Distributed Bayesian filtering using logarithmic opinion pool for dynamic sensor networks
• Distributed consensus-based multi-agent convex optimization via gradient tracking technique
• Distributed stochastic gradient tracking methods
• Fast learning rates in statistical inference through aggregation
• Personalized optimization with user's feedback
• Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
• A dual approach for optimal algorithms in distributed optimization over networks
• A stochastic averaging gradient algorithm with multi‐step communication for distributed optimization
• Non-smooth setting of stochastic decentralized convex optimization problem over time-varying graphs
• Graph-theoretic approaches for analyzing the resilience of distributed control systems: a tutorial and survey
• Differentially private distributed online learning over time‐varying digraphs via dual averaging
• Graph Topology Invariant Gradient and Sampling Complexity for Decentralized and Stochastic Optimization
• Min-max optimization over slowly time-varying graphs
• Distributed event-triggered unadjusted Langevin algorithm for Bayesian learning
• Decentralized optimization over slowly time-varying graphs: algorithms and lower bounds
• Towards accelerated rates for distributed optimization over time-varying networks
• Optimal gradient tracking for decentralized optimization
• Frequentist guarantees of distributed (non)-Bayesian inference
• Zeroth-order proximal clipped gradient method with shifts for distributed stochastic composite optimization problems with infinite variance
• FLECS: a federated learning second-order framework via compression and sketching

This page was built for publication: Fast Convergence Rates for Distributed Non-Bayesian Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4566974)