Competing with Stationary Prediction Strategies
Abstract
This paper introduces the class of stationary prediction strategies and constructs a prediction algorithm that asymptotically performs as well as the best continuous stationary strategy. We make mild compactness assumptions but no stochastic assumptions about the environment. In particular, no assumption of stationarity is made about the environment, and the stationarity of the considered strategies only means that they do not depend explicitly on time; it is natural to consider only stationary strategies for many non-stationary environments.
Cite
Text
Vovk. "Competing with Stationary Prediction Strategies." Annual Conference on Computational Learning Theory, 2007. doi:10.1007/978-3-540-72927-3_32Markdown
[Vovk. "Competing with Stationary Prediction Strategies." Annual Conference on Computational Learning Theory, 2007.](https://mlanthology.org/colt/2007/vovk2007colt-competing/) doi:10.1007/978-3-540-72927-3_32BibTeX
@inproceedings{vovk2007colt-competing,
title = {{Competing with Stationary Prediction Strategies}},
author = {Vovk, Vladimir},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2007},
pages = {439-453},
doi = {10.1007/978-3-540-72927-3_32},
url = {https://mlanthology.org/colt/2007/vovk2007colt-competing/}
}