Uni-Logo
Home Teaching Publications

Frank Hutter

Frank Hutter

 Professor

Postal address:
Institut für Informatik
Albert-Ludwigs-Universität Freiburg
Sekretariat Hutter/Maschinelles Lernen
Georges-Köhler-Allee 074
79110 Freiburg, Germany
Room:
Building 074, Room 00-017
Coordinates:
48.014472, 7.831111 (DD)
Email:
fh@cs.uni-freiburg.de
Phone:
+49 761 203-67740
Fax:
+49 761 203-54217

I'm the Head of the Machine Learning Lab. I'm lucky enough to have an amazing team; all team members are linked in the sidebar on the left.

Important information for students interested in projects, theses, or Hiwi positions

With machine learning being one of the hottest topic around, our small group is flooded with requests. To make the process efficient, please do not email me directly, but follow the instructions posted here. Also, please note that we do not offer any internships for students from other universities.
Recent News

Playing Atari with canonical evolution strategies. Our arXiv paper on playing Atari using canonical evolution strategies received a lot of media attention, mostly since our agent found and exploited a bug in the game Q*bert. See, for example, articles by BBC News, The Verge, The Inquirer, Heise, and dozens more that you find when googling for: qbert bug
Promotion to tenured full professor. I have been promoted to ``W3 Professor mit Leitungsfunktion'' (the highest academic rank in Germany). Life is good :-)

Keynote at ECML-PKDD 2017. I gave a keynote at ECMLPKDD 2017: Towards end-to-end learning and optimization. Here are the slides. We are also giving a joint tutorial and workshop on AutoML at EMCL-PKDD.
I received an ERC Starting Grant. This award of 1.5 million Euros is one of the most prestigious ones given by the European union and is designed to kickstart the career of promising young scientists. My project combines Bayesian neural networks, Bayesian optimization and reinforcement learning in order to enable more automated deep learning. More details on the faculty's website.
We are world champions in automatic machine learning (AutoML). We won both 1st place in both tracks of the ChaLearn AutoML challenge: our AutoML systems outperformed all other systems and even more than 150 teams of human experts in several phases!
Using automated structure search, our Auto-Net also won its first competition dataset (achieving 90% AUC score, compared to the 80% of the best human expert team). More details on the faculty's website.

General research interests

I am interested in all facets of intelligence, and how we can replicate it in artificial systems. In particular, I work on
  • Statistical machine learning (in particular deep learning), to learn effective representations for large amounts of very noisy data (including uncertainty quantification)
  • Automated problem solving, including knowledge representation
  • Autonomously-learning software systems, which can improve their performance over time without the need for a human in the loop
  • Sequential decision making under uncertainty, to trade off building better models of the world vs. acting better based on them
  • Scientific experimentation, to make empirical research more reproducible and to codify human experts' strategies to the point where an autonomous system can execute them.
Most of my research is of a methodological nature on the meta-level, such as machine learning methods that model & optimize the performance of other machine learning methods. These meta-level problems constitute a great `drosophila' for AI: they require representation learning, reasoning under uncertainty, bounded rationality, active learning, exploration/exploitation tradeoffs, transfer learning, and much more, but they also allow for a perfectly reproducible environment with complex dynamics and available ground truth (given enough computational power). Also, they are great from a practical perspective since their outputs are better algorithms for problems we care about.

Specific research areas

I currently focus on a few research areas that combine the general themes above:
  • Bayesian optimization -- sequential experimental design under uncertainty
  • Automated machine learning -- developing an AI that can compete with human data scientists
  • Deep learning -- automatically learning representations of the data; in particular, I work on automating structure & hyperparameter search for deep learning, and on improving optimization algorithms for deep networks
  • Automated algorithm design -- developing automated methods for parameter optimization, algorithm selection, and algorithm analysis. A few years ago, I gave a Google tech talk on this topic; you can watch it on youtube.

Affiliations

I'm a member of the Department of Computer Science at the Faculty of Engineering of the University of Freiburg. I'm affiliated with three programmes by the German Research Foundation (DFG): the Emmy Noether Programme, the Priority Programme Autonomous Learning, and the Excellence Cluster BrainLinks-BrainTools. I'm a former member of the Computer Science Department of the University of British Columbia (UBC), specifically of the Laboratory for Computational Intelligence (LCI) and the Bioinformatics and Empirical & Theoretical Algorithmics Laboratory (BETA). I'm a machine learning consultant for Zynga Inc and a co-founder of Meta-Algorithmic Technologies. I earned my PhD at UBC in 2009 and my Diplom (eq. MSc) at Darmstadt University in 2004.

I coorganized/am coorganizing the following workshops and competitions:

I'm currently on the editorial board of JAIR, area chair for NIPS 2016, senior programm committee member at IJCAI 2016, and programme committee member of ICML 2016, ICLR 2016, AAAI 2016, SAT 2016, LION 2016, GECCO 2016, and AI 2016.

For more information, please see my publication page and my academic CV (the CV is updated very irregularly).

Misc

Erdös number: 3 (Anne Condon -> Michael E. Sacks -> Paul Erdös)