Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges

Abstract Most machine learning algorithms are configured by a set of hyperparameters whose values must be carefully chosen and which often considerably impact performance. To avoid a time‐consuming and irreproducible manual process of trial‐and‐error to find well‐performing hyperparameter configurations, various automatic hyperparameter optimization (HPO) methods—for example, based on resampling error estimation for supervised machine learning—can be employed. After introducing HPO from a general perspective, this paper reviews important HPO methods, from simple techniques such as grid or random search to more advanced methods like evolution strategies, Bayesian optimization, Hyperband, and racing. This work…

• DF
  Deutsche Forschungsgemeinschaft

  Awards: SFB 876‐A3, SFB 876
• BF
  Bundesministerium für Bildung und Forschung

  Award: 01IS18036A