On Distributed Online Classification in the Midst of Concept Drifts

Abstract

In this work, we analyze the generalization ability of distributed online learning algorithms under stationary and non-stationary environments. We derive bounds for the excess-risk attained by each node in a connected network of learners and study the performance advantage that diffusion strategies have over individual non-cooperative processing. We conduct extensive simulations to illustrate the results.

19 pages, 14 figures, to appear in Neurocomputing, 2013

References in corpus (2)

• Diffusion Strategies Outperform Consensus Strategies for Distributed Estimation over Adaptive Networks
• Performance Limits for Distributed Estimation Over LMS Adaptive Networks

Cited by in corpus (7)

• Adaptive Penalty-Based Distributed Stochastic Convex Optimization
• Online Distributed Learning Over Networks in RKH Spaces Using Random Fourier Features
• Can Primal Methods Outperform Primal-dual Methods in Decentralized Dynamic Optimization?
• Tracking Performance of Online Stochastic Learners
• Asynchronous Adaptation and Learning over Networks --- Part I: Modeling and Stability Analysis
• Online Stochastic Gradient Methods Under Sub-Weibull Noise and the Polyak-Łojasiewicz Condition
• Network Classifiers With Output Smoothing