English

Optimal Non-Asymptotic Lower Bound on the Minimax Regret of Learning with Expert Advice

Machine Learning 2015-11-09 v1 Machine Learning

Abstract

We prove non-asymptotic lower bounds on the expectation of the maximum of dd independent Gaussian variables and the expectation of the maximum of dd independent symmetric random walks. Both lower bounds recover the optimal leading constant in the limit. A simple application of the lower bound for random walks is an (asymptotically optimal) non-asymptotic lower bound on the minimax regret of online learning with expert advice.

Keywords

Cite

@article{arxiv.1511.02176,
  title  = {Optimal Non-Asymptotic Lower Bound on the Minimax Regret of Learning with Expert Advice},
  author = {Francesco Orabona and David Pal},
  journal= {arXiv preprint arXiv:1511.02176},
  year   = {2015}
}