Oral
BOHB: Robust and Efficient Hyperparameter Optimization at Scale
Stefan Falkner · Aaron Klein · Frank Hutter

Wed Jul 11th 02:10 -- 02:20 PM @ A3

Modern deep learning methods are very sensitive to many hyperparameters, and, due to the long training times of state-of-the-art models, vanilla Bayesian hyperparameter optimization is typically computationally infeasible. On the other hand, bandit-based configuration evaluation approaches based on random search lack guidance and do not converge to the best configurations as quickly. Here, we propose to combine the benefits of both Bayesian optimization and bandit-based methods, in order to achieve the best of both worlds: strong anytime performance and fast convergence to optimal configurations. We propose a new practical state-of-the-art hyperparameter optimization method, which consistently outperforms both Bayesian optimization and Hyperbandon a wide range of problem types, including high-dimensional toy functions, support vector machines, feed-forward neural networks, Bayesian neural networks, deep reinforcement learning, and convolutional neural networks. Our method is robust and versatile, while at the same time being conceptually simple and easy to implement.

Author Information

Stefan Falkner (University of Freiburg)
Aaron Klein (University of Freiburg)
Frank Hutter (University of Freiburg)
Frank Hutter

Frank Hutter is a Full Professor for Machine Learning at the Computer Science Department of the University of Freiburg (Germany), where he has been a faculty member since 2013. Before that, he was at the University of British Columbia (UBC) for eight years, for his PhD and postdoc. Frank's main research interests lie in machine learning, artificial intelligence and automated algorithm design. For his 2009 PhD thesis on algorithm configuration, he received the CAIAC doctoral dissertation award for the best thesis in AI in Canada that year, and with his coauthors, he received several best paper awards and prizes in international competitions on automated machine learning, SAT solving, and AI planning. Since 2016 he holds an ERC Starting Grant for a project on automating deep learning based on Bayesian optimization, Bayesian neural networks, and deep reinforcement learning.

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors