| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 4952464 | Theoretical Computer Science | 2016 | 17 Pages |
Abstract
The main open problem from this work is whether there exists a bandit algorithm for this problem with both optimal regret of O(nT) and running time of O(n3) for either regime, or there is an inherent tradeoff between the two performance measures.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computational Theory and Mathematics
Authors
Nir Ailon, Kohei Hatano, Eiji Takimoto,