Exploiting easy data in online optimization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Exploiting easy data in online optimization

Amir Sani
Gergely Neu
  • Fonction : Auteur
  • PersonId : 961171
Alessandro Lazaric

Résumé

We consider the problem of online optimization, where a learner chooses a decision from a given decision set and suffers some loss associated with the decision and the state of the environment. The learner's objective is to minimize its cumulative regret against the best fixed decision in hindsight. Over the past few decades numerous variants have been considered, with many algorithms designed to achieve sub-linear regret in the worst case. However, this level of robustness comes at a cost. Proposed algorithms are often over-conservative, failing to adapt to the actual complexity of the loss sequence which is often far from the worst case. In this paper we introduce a general algorithm that, provided with a "safe" learning algorithm and an opportunistic "benchmark", can effectively combine good worst-case guarantees with much improved performance on "easy" data. We derive general theoretical bounds on the regret of the proposed algorithm and discuss its implementation in a wide range of applications, notably in the problem of learning with shifting experts (a recent COLT open problem). Finally, we provide numerical simulations in the setting of prediction with expert advice with comparisons to the state of the art.
Fichier principal
Vignette du fichier
SNL14.pdf (426.85 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01079428 , version 1 (01-11-2014)

Identifiants

  • HAL Id : hal-01079428 , version 1

Citer

Amir Sani, Gergely Neu, Alessandro Lazaric. Exploiting easy data in online optimization. Advances in Neural Information Processing 27, Dec 2014, Montreal, Canada. ⟨hal-01079428⟩
199 Consultations
121 Téléchargements

Partager

Gmail Facebook X LinkedIn More