@article{1670bd5fc0b34c3c9a2854d453abd4dc,
title = "Nonstochastic multi-armed bandits with graph-structured feedback",
abstract = "We introduce 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 setting naturally models several situations where 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.",
keywords = "Graph theory, Learning from experts, Learning with partial feedback, Multi-armed bandits, Online learning",
author = "Noga Alon and Nicolo Cesa-Bianchi and Claudio Gentile and Shie Mannor and Yishay Mansour and Ohad Shamir",
note = "Publisher Copyright: {\textcopyright} 2017 the authors.",
year = "2017",
doi = "10.1137/140989455",
language = "אנגלית",
volume = "46",
pages = "1785--1826",
journal = "SIAM Journal on Computing",
issn = "0097-5397",
publisher = "Society for Industrial and Applied Mathematics (SIAM)",
number = "6",
}