On Theorem 2.3 in "Prediction, Learning, and Games" by Cesa-Bianchi and Lugosi

Alexey Chernov

On Theorem 2.3 in "Prediction, Learning, and Games" by Cesa-Bianchi and Lugosi

Machine Learning 2010-11-29 v1

Authors: Alexey Chernov

Abstract

The note presents a modified proof of a loss bound for the exponentially weighted average forecaster with time-varying potential. The regret term of the algorithm is upper-bounded by sqrt{n ln(N)} (uniformly in n), where N is the number of experts and n is the number of steps.

Keywords

exponentially weighted average forecaster time-varying potential loss bound regret bound online learning

Cite

@article{arxiv.1011.5668,
  title  = {On Theorem 2.3 in "Prediction, Learning, and Games" by Cesa-Bianchi and Lugosi},
  author = {Alexey Chernov},
  journal= {arXiv preprint arXiv:1011.5668},
  year   = {2010}
}

Comments

3 pages; excerpt from arXiv:1005.1918, simplified and rewritten using the notation of the monograph by Cesa-Bianchi and Lugosi

Related papers

View all related →