AutoML.org

Freiburg-Hannover

DEHB

DEHB: EVOLUTIONARY HYPERBAND FOR SCALABLE, ROBUST AND EFFICIENT HYPERPARAMETER OPTIMIZATION By Noor Awad, Modern machine learning algorithms crucially rely on several design decisions to achieve strong performance, making the problem of Hyperparameter Optimization (HPO) more important than ever. We believe that a practical, general HPO method must fulfill many desiderata, including: (1) strong anytime performance, […]

Read More

Playing Games with Progressive Episode Lengths

By A framework of ES-based limited episode’s length

Read More