no code implementations • 18 Jun 2019 • Prabhant Singh, Tobias Jacobs, Sebastien Nicolas, Mischa Schmidt
As a surprising result, we find that the learning curves are completely flat, i. e., there is no observable progress of the controller in terms of the performance of its generated architectures.
1 code implementation • 15 Apr 2019 • Mischa Schmidt, Shahd Safarani, Julia Gastinger, Tobias Jacobs, Sebastien Nicolas, Anett Schülke
This empirical study involves a range of different machine learning algorithms and datasets with various characteristics to compare the performance of Differential Evolution with Sequential Model-based Algorithm Configuration (SMAC), a reference Bayesian Optimization approach.