Online Learning of Non-stationary Sequences
Author(s)Monteleoni, Claire; Jaakkola, Tommi
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 of the switching-rate parameter that governs the switching dynamics. We demonstrate the algorithm in the context of wireless networks.
Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory
AI, online learning, regret bounds, non-stationarity, HMM, wireless networks