Prediction with Expert Advice under Discounted Loss
Machine Learning
2010-06-07 v2
Abstract
We study prediction with expert advice in the setting where the losses are accumulated with some discounting---the impact of old losses may gradually vanish. We generalize the Aggregating Algorithm and the Aggregating Algorithm for Regression to this case, propose a suitable new variant of exponential weights algorithm, and prove respective loss bounds.
Keywords
Cite
@article{arxiv.1005.1918,
title = {Prediction with Expert Advice under Discounted Loss},
author = {Alexey Chernov and Fedor Zhdanov},
journal= {arXiv preprint arXiv:1005.1918},
year = {2010}
}
Comments
26 pages; expanded (2 remarks -> theorems), some misprints corrected