Online Learning with Feedback Graphs Without the Graphs.

Alon Cohen, Tamir Hazan, Tomer Koren

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We study an online learning framework introduced by Mannor and Shamir (2011) in which the feedback is specified by a graph, in a setting where the graph may vary from round to round and is \emphnever fully revealed to the learner. We show a large gap between the adversarial and the stochastic cases. In the adversarial case, we prove that even for dense feedback graphs, the learner cannot improve upon a trivial regret bound obtained by ignoring any additional feedback besides her own loss. In contrast, in the stochastic case we give an algorithm that achieves \widetildeΘ(\sqrtαT) regret over T rounds, provided that the independence numbers of the hidden feedback graphs are at most α. We also extend our results to a more general feedback model, in which the learner does not necessarily observe her own loss, and show that, even in simple cases, concealing the feedback graphs might render the problem unlearnable.
Original languageEnglish
Title of host publicationInternational Conference on Machine Learning, 20-22 June 2016, New York, New York, USA
EditorsMaria Florina Balcan, Kilian Q. Weinberger
Pages811-819
Number of pages9
StatePublished - 2016
Externally publishedYes
Event33rd International Conference on Machine Learning, ICML 2016 - New York City, United States
Duration: 19 Jun 201624 Jun 2016

Publication series

NameProceedings of Machine Learning Research
PublisherPMLR
Volume48

Conference

Conference33rd International Conference on Machine Learning, ICML 2016
Country/TerritoryUnited States
CityNew York City
Period19/06/1624/06/16

Fingerprint

Dive into the research topics of 'Online Learning with Feedback Graphs Without the Graphs.'. Together they form a unique fingerprint.

Cite this