Entropy Search for Information-Efficient Global Optimization





Contemporary global optimization algorithms are based on local measures of utility, rather than a probability measure over location and value of the optimum. They thus attempt to collect low function values, not to learn about the optimum. The reason for the absence of probabilistic global optimizers is that the corresponding inference problem is intractable in several ways. This paper develops desiderata for probabilistic optimization algorithms, then presents a concrete algorithm which addresses each of the computational intractabilities with a sequence of approximations and explicitly adresses the decision problem of maximizing information gain from each evaluation.

Author(s): Hennig, P. and Schuler, CJ.
Journal: Journal of Machine Learning Research
Volume: 13
Pages: 1809-1837
Year: 2012
Month: June
Day: 0

Department(s): Empirical Inference, Probabilistic Numerics
Research Project(s): Automatic Controller Tuning using Bayesian Optimization
Bayesian Optimization
Probabilistic Inference
Bibtex Type: Article (article)

Event Name: -

Links: PDF


  title = {Entropy Search for Information-Efficient Global Optimization},
  author = {Hennig, P. and Schuler, CJ.},
  journal = {Journal of Machine Learning Research},
  volume = {13},
  pages = {1809-1837},
  month = jun,
  year = {2012},
  month_numeric = {6}