Search
Now showing items 1-2 of 2
Online Learning of Non-stationary Sequences
(2003-06-12)
We consider an online learning scenario in which the learner can make predictions on the basis of a fixed set of experts. The performance of each expert may change over time in a manner unknown to the learner. We formulate ...
Online Learning of Non-stationary Sequences
(2005-11-17)
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 ...