ICML 2015poster40 citations

The Hedge Algorithm on a Continuum

Walid Krichene, Maximilian Balandat, Claire Tomlin, Alexandre Bayen

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(\sqrtt \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.

BibTeX
@InProceedings{pmlr-v37-krichene15,
  title = 	 {The Hedge Algorithm on a Continuum},
  author = 	 {Krichene, Walid and Balandat, Maximilian and Tomlin, Claire and Bayen, Alexandre},
  booktitle = 	 {Proceedings of the 32nd International Conference on Machine Learning},
  pages = 	 {824--832},
  year = 	 {2015},
  editor = 	 {Bach, Francis and Blei, David},
  volume = 	 {37},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {Lille, France},
  month = 	 {07--09 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v37/krichene15.pdf},
  url = 	 {https://proceedings.mlr.press/v37/krichene15.html},
  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(\sqrtt \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.}
}