Timezone: »

6th ICML Workshop on Automated Machine Learning (AutoML 2019)
Frank Hutter · Joaquin Vanschoren · Katharina Eggensperger · Matthias Feurer · Matthias Feurer

Fri Jun 14 08:30 AM -- 06:00 PM (PDT) @ Grand Ballroom B
Event URL: https://sites.google.com/view/automl2019icml/ »

Machine learning has achieved considerable successes in recent years, but this success often relies on human experts, who construct appropriate features, design learning architectures, set their hyperparameters, and develop new learning algorithms. Driven by the demand for off-the-shelf machine learning methods from an ever-growing community, the research area of AutoML targets the progressive automation of machine learning aiming to make effective methods available to everyone. The workshop targets a broad audience ranging from core machine learning researchers in different fields of ML connected to AutoML, such as neural architecture search, hyperparameter optimization, meta-learning, and learning to learn, to domain experts aiming to apply machine learning to new types of problems.

Fri 9:00 a.m. - 9:05 a.m.
Welcome (Presentation)
Frank Hutter
Fri 9:05 a.m. - 9:40 a.m.
[ Video

Bayesian optimization is a powerful and flexible tool for AutoML. While BayesOpt was first deployed for AutoML simply as a black-box optimizer, recent approaches perform grey-box optimization: they leverage capabilities and problem structure specific to AutoML such as freezing and thawing training, early stopping, treating cross-validation error minimization as multi-task learning, and warm starting from previously tuned models. We provide an overview of this area and describe recent advances for optimizing sampling-based acquisition functions that make grey-box BayesOpt significantly more efficient.

Peter I Frazier
Fri 9:40 a.m. - 11:00 a.m.
Poster Session 1 (all papers) (Poster Session)
Matilde Gargiani, Yochai Zur, Chaim Baskin, Evgenii Zheltonozhskii, Liam Li, Ameet Talwalkar, Xuedong Shang, HARKIRAT Behl, Atilim Gunes Baydin, Ivo Couckuyt, Tom Dhaene, Chieh Hubert Lin, Wei Wei, Min Sun, Orchid Majumder, Michele Donini, Yoshihiko Ozaki, Ryan P. Adams, Christian Geißler, Ping Luo, zhanglin peng, shaowenqi, Ruimao Zhang, John Langford, Rich Caruana, Debadeepta Dey, Charles Weill, Xavi Gonzalvo, Scott Yang, Scott Yak, Eugen Hotaj, vlejd Macko, Mehryar Mohri, Corinna Cortes, Stefan Webb, JP 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, Ken 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, hugojair 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
Fri 11:00 a.m. - 11:35 a.m.
[ Video

The mission of AutoML is to make ML available for non-ML experts and to accelerate research on ML. We have a very similar mission at fast.ai and have helped over 200,000 non-ML experts use state-of-the-art ML (via our research, software, & teaching), yet we do not use methods from the AutoML literature. I will share several insights we've learned through this work, with the hope that they may be helpful to AutoML researchers.

Fri 11:35 a.m. - 12:00 p.m.
Contributed Talk 1: A Boosting Tree Based AutoML System for Lifelong Machine Learning (Contributed Talk) [ Video
Zheng Xiong
Fri 12:00 p.m. - 12:50 p.m.
Poster Session 2 (all papers) (Poster Session)
Fri 12:50 p.m. - 2:00 p.m.
Lunch Break (Break)
Fri 2:00 p.m. - 2:35 p.m.
[ Video

In this talk I'll survey work by Google researchers over the past several years on the topic of AutoML, or learning-to-learn. The talk will touch on basic approaches, some successful applications of AutoML to a variety of domains, and sketch out some directions for future AutoML systems that can leverage massively multi-task learning systems for automatically solving new problems.

Jeff Dean
Fri 2:35 p.m. - 3:00 p.m.
Contributed Talk 2: Transfer NAS: Knowledge Transfer between Search Spaces with Transformer Agents (Contributed Talk) [ Video
Zalán Borsos
Fri 3:00 p.m. - 4:00 p.m.
Poster Session 3 (all papers) (Poster Session)
Fri 4:00 p.m. - 4:25 p.m.
Contributed Talk 3: Random Search and Reproducibility for Neural Architecture Search (Contributed Talk) [ Video
Liam Li
Fri 4:25 p.m. - 5:00 p.m.
[ Video

The practical work of deploying a machine learning system is dominated by issues outside of training a model: data preparation, data cleaning, understanding the data set, debugging models, and so on. What does it mean to apply ML to this “grunt work” of machine learning and data science? I will describe first steps towards tools in these directions, based on the idea of semi-automating ML: using unsupervised learning to find patterns in the data that can be used to guide data analysts. I will also describe a new notebook system for pulling these tools together: if we augment Jupyter-style notebooks with data-flow and provenance information, this enables a new class of data-aware notebooks which are much more natural for data manipulation.

Charles Sutton
Fri 5:00 p.m. - 6:00 p.m.
Panel Discussion (Panel) [ Video
Wenpeng Zhang, Charles Sutton, Liam Li, RACHEL Thomas, Erin LeDell
Fri 6:00 p.m. - 6:10 p.m.
Closing Remarks (Presentation)
Frank Hutter

Author Information

Frank Hutter (University of Freiburg and Bosch Center for Artificial Intelligence)
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.

Joaquin Vanschoren (Eindhoven University of Technology)
Katharina Eggensperger (University of Freiburg)
Matthias Feurer (University of Freiburg)
Matthias Feurer (University of Freiburg)

More from the Same Authors