Online learning with a hint
Name
7114-online-learning-with-a-hint.pdf
Description
Published version
Size
550.36 KB
Format
Unknown
Checksum (MD5)
bb6bad80ed9e1bd390480c1700905290
Author(s)
Dekel, Ofer
Flajolet, Arthur
Haghtalab, Nika
Jaillet, Patrick
Date Issued
2017
Citation
Jaillet, Patrick. 2017. "Online learning with a hint."
Version
Final published version
Abstract
© 2017 Neural information processing systems foundation. All rights reserved. We study a variant of online linear optimization where the player receives a hint about the loss function at the beginning of each round. The hint is given in the form of a vector that is weakly correlated with the loss vector on that round. We show that the player can benefit from such a hint if the set of feasible actions is sufficiently round. Specifically, if the set is strongly convex, the hint can be used to guarantee a regret of O(log(T)), and if the set is q-uniformly convex for q ∈ (2, 3), the hint can be used to guarantee a regret of o(√T). In contrast, we establish Ω(VT) lower bounds on regret when the set of feasible actions is a polyhedron.
MIT Department
Massachusetts Institute of Technology. Operations Research Center
Massachusetts Institute of Technology. Laboratory for Information and Decision Systems
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/7114-online-learning-with-a-hint
