Tracking the Best of Many Experts
Abstract
An algorithm is presented for online prediction that allows to track the best expert efficiently even if the number of experts is exponentially large, provided that the set of experts has a certain structure allowing efficient implementations of the exponentially weighted average predictor. As an example we work out the case where each expert is represented by a path in a directed graph and the loss of each expert is the sum of the weights over the edges in the path.
Cite
Text
György et al. "Tracking the Best of Many Experts." Annual Conference on Computational Learning Theory, 2005. doi:10.1007/11503415_14Markdown
[György et al. "Tracking the Best of Many Experts." Annual Conference on Computational Learning Theory, 2005.](https://mlanthology.org/colt/2005/gyorgy2005colt-tracking/) doi:10.1007/11503415_14BibTeX
@inproceedings{gyorgy2005colt-tracking,
title = {{Tracking the Best of Many Experts}},
author = {György, András and Linder, Tamás and Lugosi, Gábor},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2005},
pages = {204-216},
doi = {10.1007/11503415_14},
url = {https://mlanthology.org/colt/2005/gyorgy2005colt-tracking/}
}