I'm head of the Research Group on Machine Learning for Automated Algorithm Design. I'm lucky enough to have an amazing team; all team members are linked in the sidebar on the left.

We placed 2nd in the AutoML track and 1st in the tweakathon track of the second round of the ChaLearn AutoML challenge. (11 September 2015)

Together with our close collaborators at UBC, we placed 1st, 2nd, and 3rd in the ICON Challenge on Algorithm Selection. First with SATzilla, second with AutoFolio (first place on PAR10 score and number of solved instances), and third with a combination of the two. (29 July 2015)

Five awards at the IPC 2014 Planning and Learning Track! Fast Downward Cedalion won the best learner award and Fast Downward SMAC won the best basic solver award. FD Cedalion also got second place in the overall best quality category, and FD SMAC got third place in the categories overall best quality and best learner.

General research interests

• Statistical machine learning (in particular deep learning), to model the data
• Optimization, to make optimal decisions given the data
• Artificial intelligence, in particular automated problem solving
• Autonomously learning software systems, which can improve their performance over time without the need for a human in the loop
• Scientific experimentation, to make empirical research more reproducible and to codify human experts' strategies to the point where an autonomous system can execute them.

Specific research areas

• 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. I recently 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 the following workshops and competitions:

• ICML workshops on Automated Machine Learning: AutoML 2014 & AutoML 2015
• AAAI workshop on Algorithm Configuration: AlgoConf 2015
• Workshop on Algorithm Configuration & Selection: COSEAL 2014
• NIPS workshops on Bayesian Optimization: BayesOpt 2011 & BayesOpt 2012
• Configurable SAT Solver Challenge: CSSC 2013 & CSSC 2014

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.

Misc

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