Online Learning with Feedback Graphs Without the Graphs
Alon Cohen, Tamir Hazan, Tomer Koren
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.
BibTeX
@InProceedings{pmlr-v48-cohena16,
title = {Online Learning with Feedback Graphs Without the Graphs},
author = {Cohen, Alon and Hazan, Tamir and Koren, Tomer},
booktitle = {Proceedings of The 33rd International Conference on Machine Learning},
pages = {811--819},
year = {2016},
editor = {Balcan, Maria Florina and Weinberger, Kilian Q.},
volume = {48},
series = {Proceedings of Machine Learning Research},
address = {New York, New York, USA},
month = {20--22 Jun},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v48/cohena16.pdf},
url = {https://proceedings.mlr.press/v48/cohena16.html},
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.}
}