The Hedge Algorithm on a Continuum

Abstract

We consider an online optimization problem on a subset S of R^n (not necessarily convex), in which a decision maker chooses, at each iteration t, a probability distribution x^(t) over S, and seeks to minimize a cumulative expected loss, where each loss is a Lipschitz function revealed at the end of iteration t. Building on previous work, we propose a generalized Hedge algorithm and show a O(\sqrt{t} \log t) bound on the regret when the losses are uniformly Lipschitz and S is uniformly fat (a weaker condition than convexity). Finally, we propose a generalization to the dual averaging method on the set of Lebesgue-continuous distributions over S.

Cite

Text

Krichene et al. "The Hedge Algorithm on a Continuum." International Conference on Machine Learning, 2015.

Markdown

[Krichene et al. "The Hedge Algorithm on a Continuum." International Conference on Machine Learning, 2015.](https://mlanthology.org/icml/2015/krichene2015icml-hedge/)

BibTeX

@inproceedings{krichene2015icml-hedge,
  title     = {{The Hedge Algorithm on a Continuum}},
  author    = {Krichene, Walid and Balandat, Maximilian and Tomlin, Claire and Bayen, Alexandre},
  booktitle = {International Conference on Machine Learning},
  year      = {2015},
  pages     = {824-832},
  volume    = {37},
  url       = {https://mlanthology.org/icml/2015/krichene2015icml-hedge/}
}