Skip to main content
Log in
(current)
MIT Open Scholarship
DSpace@MIT
Search
Home
MIT Open Access Articles
MIT Open Access Articles
Online learning with a hint
This is not the latest version of this item. The latest version can be found
here
.
Online learning with a hint
Download
Name
7114-online-learning-with-a-hint.pdf
Description
Published version
Show more
Size
550.36 KB
Format
Adobe PDF
Checksum
(MD5)
bb6bad80ed9e1bd390480c1700905290
Show more
sword-2019-05-31T18:00:14.original.xml (130 B)
Original SWORD entry document
Show more
Author(s)
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.
Show more
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
https://hdl.handle.net/1721.1/137673
DOI of Published Version
https://papers.nips.cc/paper/7114-online-learning-with-a-hint
