2014/09/30 by Noga Alon, Alon, Noga, Nicolò Cesa-Bianchi +9 · 6 citations
Computer Science · Mathematics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1409.8428
Preliminary versions of parts of this paper appeared in [1,20], and also as arXiv papers arXiv:1106.2436 and arXiv:1307.4564
arxiv created 2014/09/30 · arxiv updated 2014/10/01
We present and study a partial-information model of online learning, where a decision maker repeatedly chooses from a finite set of actions, and observes some subset of the associated losses. This naturally models several situations where the losses of different actions are related, and knowing the loss of one action provides information on the loss of other actions. Moreover, it generalizes and interpolates between the well studied full-information setting (where all losses are revealed) and the bandit setting (where only the loss of the action chosen by the player is revealed). We provide several algorithms addressing different variants of our setting, and provide tight regret bounds depending on combinatorial properties of the information feedback structure.