Universal linear least-squares prediction
Andrew C. Singer, Meir Feder · 2002
An approach to the problem of linear prediction is discussed that is based on previous developments in the universal coding and computational learning theory literature. This development provides a novel perspective on the adaptive filtering problem, and represents a significant departure from traditional adaptive filtering methodologies. In this context, we demonstrate a sequential algorithm for linear prediction whose accumulated squared prediction error, for every possible sequence, is asymptotically as small as the best fixed linear predictor for that sequence.