Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design

Loading...
Thumbnail Image
Penn collection
Statistics Papers
Degree type
Discipline
Subject
Statistics and Probability
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Srinivas, Niranjan
Krause, Andreas
Kakade, Sham M
Seeger, Matthias
Contributor
Abstract

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 RKHS norm. We resolve the important open problem of deriving regret bounds for this setting, which imply novel convergence rates for GP optimization. We analyze GP-UCB, an intuitive upper-confidence based algorithm, and bound its cumulative regret in terms of maximal information gain, establishing a novel connection between GP optimization and experimental design. Moreover, by bounding the latter in terms of operator spectra, we obtain explicit sublinear regret bounds for many commonly used covariance functions. In some important cases, our bounds have surprisingly weak dependence on the dimensionality. In our experiments on real sensor data, GP-UCB compares favorably with other heuristical GP optimization approaches.

Advisor
Date of presentation
2010-01-01
Conference name
Statistics Papers
Conference dates
2023-05-17T15:27:24.000
Conference location
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Recommended citation
Collection