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_32

Markdown

[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_32

BibTeX

@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/}
}