Online Learning of Non-stationary Sequences

We consider an online learning scenario in which the learner can make predictions on the basis of a fixed set of experts. We derive upper and lower relative loss bounds for a class of universal learning algorithms involving a switching dynamics over the choice of the experts. On the basis of the performance bounds we provide the optimal a priori discretization for learning the parameter that governs the switching dynamics. We demonstrate the new algorithm in the context of wireless networks.

• Type: Conference
• Year: 2003
• Where: NIPS
• Authors: Claire Monteleoni, Tommi Jaakkola
• Keywords: NIPS 2003, NIPS 2007, Online Learning Scenario, Relative Loss Bounds, Switching Dynamics