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

  title={Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting},
  author={Niranjan Srinivas and Andreas Krause and Sham M. Kakade and Matthias W. Seeger},
  journal={IEEE Transactions on Information Theory},
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 important open problem of deriving regret bounds for this setting, which imply novel convergence rates for GP optimization. We analyze an intuitive Gaussian process upper confidence bound (GP-UCB) algorithm… CONTINUE READING
Highly Influential
This paper has highly influenced 28 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 174 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 2 times over the past 90 days. VIEW TWEETS


Publications citing this paper.
Showing 1-10 of 116 extracted citations

174 Citations

Citations per Year
Semantic Scholar estimates that this publication has 174 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 32 references

Gaussian process modelling of dependencies in multi-armed bandit problems

  • L. Dorard, D. Glowacka, J. Shawe-Taylor
  • In Int. Symp. Op. Res.,
  • 2009
1 Excerpt

Gaussian process optimization in the bandit setting: No regret and experimental design

  • N. Srinivas, A. Krause, S. Kakade, M. Seeger
  • 2009
2 Excerpts

Similar Papers

Loading similar papers…