University of Cambridge > Talks.cam > Machine Learning @ CUED > Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹ️ Information

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

Download to your calendar using vCal

If you have a question about this talk, please contact Peter Orbanz .

Many applications require optimizing an unknown, noisy function that is expensive to evaluate. We formalize this task as a multi- armed 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-con dence 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.

This talk is part of the Machine Learning @ CUED series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

LR3, Engineering Department, Baker Building Centre for Mathematical Sciences List 1

Other talks

Topic Film, TV shows for Medical Education, ‘The Wire’ as a case study TBC Cambridge RNA Club - IN PERSON Morning Break Group Work Ensemble inequivalence for systems with long-range interactions
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity