๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting

โœ Scribed by Srinivas, N.; Krause, A.; Kakade, S.M.; Seeger, M.


Book ID
114643061
Publisher
IEEE
Year
2012
Tongue
English
Weight
963 KB
Volume
58
Category
Article
ISSN
0018-9448

No coin nor oath required. For personal study only.


๐Ÿ“œ SIMILAR VOLUMES


Information-Theoretic Regret Bounds for
โœ Srinivas, N.; Krause, A.; Kakade, S.M.; Seeger, M. ๐Ÿ“‚ Article ๐Ÿ“… 2012 ๐Ÿ› IEEE ๐ŸŒ English โš– 963 KB

Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multiarmed bandit problem, where the payoff function is either sampled from a Gaussian process (GP) or has low norm in a reproducing kernel Hilbert space. We resolve the importa