Timezone: »
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 Hyperband on 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 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)
-
2018 Oral: BOHB: Robust and Efficient Hyperparameter Optimization at Scale »
Wed. Jul 11th 12:10 -- 12:20 PM Room A3
More from the Same Authors
-
2021 : Dynamic Pruning of a Neural Network via Gradient Signal-to-Noise Ratio »
Julien N Siems · Aaron Klein · Cedric Archambeau · Maren Mahsereci -
2021 : Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization »
Sergio Izquierdo · Julia Guerrero-Viu · Sven Hauns · Guilherme Miotto · Simon Schrodi · André Biedenkapp · Thomas Elsken · Difan Deng · Marius Lindauer · Frank Hutter -
2022 : P30: Meta-Learning Real-Time Bayesian AutoML For Small Tabular Data »
Frank Hutter · Katharina Eggensperger -
2022 : On the Importance of Hyperparameters and Data Augmentation for Self-Supervised Learning »
Diane Wagner · Fabio Ferreira · Danny Stoll · Robin Tibor Schirrmeister · Samuel Gabriel Müller · Frank Hutter -
2023 Poster: Optimizing Hyperparameters with Conformal Quantile Regression »
David Salinas · Jacek Golebiowski · Aaron Klein · Matthias Seeger · Cedric Archambeau -
2023 Poster: Transformers Are Flexible Models for Real-World Bayesian Optimization »
Samuel Gabriel Müller · Matthias Feurer · Noah Hollmann · Frank Hutter -
2022 Poster: Zero-shot AutoML with Pretrained Models »
Ekrem Öztürk · Fabio Ferreira · Hadi S Jomaa · Lars Schmidt-Thieme · Josif Grabocka · Frank Hutter -
2022 Spotlight: Zero-shot AutoML with Pretrained Models »
Ekrem Öztürk · Fabio Ferreira · Hadi S Jomaa · Lars Schmidt-Thieme · Josif Grabocka · Frank Hutter -
2021 Workshop: 8th ICML Workshop on Automated Machine Learning (AutoML 2021) »
Gresa Shala · Frank Hutter · Joaquin Vanschoren · Marius Lindauer · Katharina Eggensperger · Colin White · Erin LeDell -
2021 Poster: Self-Paced Context Evaluation for Contextual Reinforcement Learning »
Theresa Eimer · André Biedenkapp · Frank Hutter · Marius Lindauer -
2021 Poster: TempoRL: Learning When to Act »
André Biedenkapp · Raghu Rajan · Frank Hutter · Marius Lindauer -
2021 Spotlight: TempoRL: Learning When to Act »
André Biedenkapp · Raghu Rajan · Frank Hutter · Marius Lindauer -
2021 Spotlight: Self-Paced Context Evaluation for Contextual Reinforcement Learning »
Theresa Eimer · André Biedenkapp · Frank Hutter · Marius Lindauer -
2021 Poster: BORE: Bayesian Optimization by Density-Ratio Estimation »
Louis Chi-Chun Tiao · Aaron Klein · Matthias W Seeger · Edwin V Bonilla · Cedric Archambeau · Fabio Ramos -
2021 Oral: BORE: Bayesian Optimization by Density-Ratio Estimation »
Louis Chi-Chun Tiao · Aaron Klein · Matthias W Seeger · Edwin V Bonilla · Cedric Archambeau · Fabio Ramos -
2020 Workshop: 7th ICML Workshop on Automated Machine Learning (AutoML 2020) »
Frank Hutter · Joaquin Vanschoren · Marius Lindauer · Charles Weill · Katharina Eggensperger · Matthias Feurer · Matthias Feurer -
2020 : Welcome »
Frank Hutter -
2019 : Closing Remarks »
Frank Hutter -
2019 : Poster Session 1 (all papers) »
Matilde Gargiani · Yochai Zur · Chaim Baskin · Evgenii Zheltonozhskii · Liam Li · Ameet Talwalkar · Xuedong Shang · Harkirat Singh Behl · Atilim Gunes Baydin · Ivo Couckuyt · Tom Dhaene · Chieh Lin · Wei Wei · Min Sun · Orchid Majumder · Michele Donini · Yoshihiko Ozaki · Ryan P. Adams · Christian Geißler · Ping Luo · zhanglin peng · · Ruimao Zhang · John Langford · Rich Caruana · Debadeepta Dey · Charles Weill · Xavi Gonzalvo · Scott Yang · Scott Yak · Eugen Hotaj · Vladimir Macko · Mehryar Mohri · Corinna Cortes · Stefan Webb · Jonathan Chen · Martin Jankowiak · Noah Goodman · Aaron Klein · Frank Hutter · Mojan Javaheripi · Mohammad Samragh · Sungbin Lim · Taesup Kim · SUNGWOONG KIM · Michael Volpp · Iddo Drori · Yamuna Krishnamurthy · Kyunghyun Cho · Stanislaw Jastrzebski · Quentin de Laroussilhe · Mingxing Tan · Xiao Ma · Neil Houlsby · Andrea Gesmundo · Zalán Borsos · Krzysztof Maziarz · Felipe Petroski Such · Joel Lehman · Kenneth Stanley · Jeff Clune · Pieter Gijsbers · Joaquin Vanschoren · Felix Mohr · Eyke Hüllermeier · Zheng Xiong · Wenpeng Zhang · Wenwu Zhu · Weijia Shao · Aleksandra Faust · Michal Valko · Michael Y Li · Hugo Jair Escalante · Marcel Wever · Andrey Khorlin · Tara Javidi · Anthony Francis · Saurajit Mukherjee · Jungtaek Kim · Michael McCourt · Saehoon Kim · Tackgeun You · Seungjin Choi · Nicolas Knudde · Alexander Tornede · Ghassen Jerfel -
2019 : Welcome »
Frank Hutter -
2019 Workshop: 6th ICML Workshop on Automated Machine Learning (AutoML 2019) »
Frank Hutter · Joaquin Vanschoren · Katharina Eggensperger · Matthias Feurer · Matthias Feurer -
2019 Poster: NAS-Bench-101: Towards Reproducible Neural Architecture Search »
Chris Ying · Aaron Klein · Eric Christiansen · Esteban Real · Kevin Murphy · Frank Hutter -
2019 Oral: NAS-Bench-101: Towards Reproducible Neural Architecture Search »
Chris Ying · Aaron Klein · Eric Christiansen · Esteban Real · Kevin Murphy · Frank Hutter -
2019 Tutorial: Algorithm configuration: learning in the space of algorithm designs »
Kevin Leyton-Brown · Frank Hutter