Optimistic Optimization of a Deterministic Function without the Knowledge of its Smoothness

  title={Optimistic Optimization of a Deterministic Function without the Knowledge of its Smoothness},
  author={R{\'e}mi Munos},
We consider a global optimization problem of a deterministic function f in a semimetric space, given a finite budget of n evaluations. The function f is assumed to be locally smooth (around one of its global maxima) with respect to a semi-metric l. We describe two algorithms based on optimistic exploration that use a hierarchical partitioning of the space at all scales. A first contribution is an algorithm, DOO, that requires the knowledge of l. We report a finite-sample performance bound in… CONTINUE READING
Highly Influential
This paper has highly influenced 15 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 63 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 42 extracted citations

63 Citations

Citations per Year
Semantic Scholar estimates that this publication has 63 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 27 references

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

  • Niranjan Srinivas, Andreas Krause, Sham Kakade, Matthias Seeger
  • International Conference on Machine Learning…
  • 2010
1 Excerpt

Open loop optimistic planning

  • S. Bubeck, R. Munos
  • Conference on Learning Theory
  • 2010

Cs . Szepesvári . X - armed bandits

  • R. Munos, G. Stoltz
  • Advances in Neural Information Processing Systems
  • 2008

Similar Papers

Loading similar papers…