2000 character limit reached
On Distributed Online Classification in the Midst of Concept Drifts (1301.0047v1)
Published 1 Jan 2013 in math.OC, cs.DC, cs.LG, cs.SI, and physics.soc-ph
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.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.