Prediction with Expert Advice Under Discounted Loss

ALT 2010 pp. 255-269

doi:10.1007/978-3-642-16108-7_22 /alt/2010/chernov2010alt-prediction/

Abstract

We study prediction with expert advice in the setting where the losses are accumulated with some discounting and the impact of old losses can gradually vanish. We generalize the Aggregating Algorithm and the Aggregating Algorithm for Regression, propose a new variant of exponentially weighted average algorithm, and prove bounds on the cumulative discounted loss.

PDF ALT Semantic Scholar

Cite

Text

Chernov and Zhdanov. "Prediction with Expert Advice Under Discounted Loss." International Conference on Algorithmic Learning Theory, 2010. doi:10.1007/978-3-642-16108-7_22

Markdown

[Chernov and Zhdanov. "Prediction with Expert Advice Under Discounted Loss." International Conference on Algorithmic Learning Theory, 2010.](https://mlanthology.org/alt/2010/chernov2010alt-prediction/) doi:10.1007/978-3-642-16108-7_22

BibTeX

@inproceedings{chernov2010alt-prediction,
  title     = {{Prediction with Expert Advice Under Discounted Loss}},
  author    = {Chernov, Alexey V. and Zhdanov, Fedor},
  booktitle = {International Conference on Algorithmic Learning Theory},
  year      = {2010},
  pages     = {255-269},
  doi       = {10.1007/978-3-642-16108-7_22},
  url       = {https://mlanthology.org/alt/2010/chernov2010alt-prediction/}
}