@article{Singer2006UniversalCT,
title={Universal Context Tree Least Squares Prediction},
author={A. C. Singer and S. S. Kozat},
journal={2006 IEEE International Symposium on Information Theory},
year={2006},
pages={426-430}
}

We investigate the problem of sequential prediction of individual sequences using a competitive algorithm approach. We have previously developed prediction algorithms that are universal with respect to the class of all linear predictors, such that the prediction algorithm competes against a continuous class of prediction algorithms, under the square error loss. In this paper, we introduce the use of a "context tree," to compete against a doubly exponential number of piecewise linear models. We… CONTINUE READING