Abstract: 

In this talk, I will discuss the technical methods behind recent progress towards robust and efficient AutoML systems. After a brief recap of the early AutoML systems Auto-WEKA and Auto-sklearn, I will discuss the next generation, Auto-learn 2.0 and Auto-PyTorch. The talk will focus on the components that make these approaches far more efficient than Auto-sklearn 1.0, including practical considerations, multi-fidelity optimization, portfolio construction, and automated policy selection.

Bio: 

Frank Hutter is a Full Professor for Machine Learning at the Computer Science Department of the University of Freiburg (Germany), as well as Chief Expert AutoML at the Bosch Center for Artificial Intelligence.
Frank holds a PhD from the University of British Columbia (UBC, 2009) and a Diplom (eq. MSc) from TU Darmstadt (2004). He received the 2010 CAIAC doctoral dissertation award for the best thesis in AI in Canada, and with his coauthors, several best paper awards and prizes in international competitions on machine learning, SAT solving, and AI planning. He is the recipient of a 2013 Emmy Noether Fellowship, a 2016 ERC Starting Grant, a 2018 Google Faculty Research Award, a 2020 ERC PoC Award, and he is a Fellow of ELLIS. Frank's recent research focuses on automated machine learning (AutoML), where he co-organized the ICML workshop series on AutoML every year since its inception in 2014, co-authored the prominent AutoML tools Auto-WEKA, Auto-sklearn, and Auto-PyTorch, won the first two AutoML challenges with his team, co-authored the first book on AutoML, worked extensively on efficient hyperparameter optimization and neural architecture search, and gave a NeurIPS 2018 tutorial with over 3000 attendees.