• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. Bayesian Optimization for Min Max Optimization
 
  • Details
  • Full
Options
2020
Presentation
Title

Bayesian Optimization for Min Max Optimization

Title Supplement
Paper presented at Workshop on Real World Experiment Design and Active Learning at ICML 2020, Virtual Workshop, 18 July 2020
Abstract
A solution that is only reliable under favourable conditions is hardly a safe solution. Min Max Optimization is an approach that returns optima that are robust against worst case conditions. We propose algorithms that perform Min Max Optimization in a setting where the function that should be optimized is not known a priori and hence has to be learned by experiments. Therefore we extend the Bayesian Optimization setting, which is tailored to maximization problems, to Min Max Optimization problems. While related work extends the two acquisition functions Expected Improvement and Gaussian Process Upper Confidence Bound; we extend the two acquisition functions Entropy Search and Knowledge Gradient. These acquisition functions are able to gain knowledge about the optimum instead of just looking for points that are supposed to be optimal. In our evaluation we show that these acquisition functions allow for better solutions - converging faster to the optimum than the benchmark settings.
Author(s)
Weichert, Dorina  
Kister, Alexander  
Conference
Workshop on Real World Experiment Design and Active Learning 2020  
International Conference on Machine Learning (ICML) 2020  
File(s)
Download (317.54 KB)
Rights
Use according to copyright law
DOI
10.24406/publica-fhg-408419
Language
English
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS  
Keyword(s)
  • Bayesian Optimization

  • Min Max Optimization

  • Worst Case Robustness

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024