Timezone: »

Algorithm configuration: learning in the space of algorithm designs
Kevin Leyton-Brown · Frank Hutter

Mon Jun 10 03:45 PM -- 06:00 PM (PDT) @ Grand Ballroom

This tutorial surveys work at a new frontier of machine learning, where each point in the hypothesis space corresponds to an algorithm, such as a combinatorial optimization problem solver. Much of this work falls under the umbrella of so-called \emph{algorithm configuration}; it also draws on methods from bandits, Bayesian optimization, reinforcement learning, and more. The tutorial will begin by explaining the area, describing some recent success stories, and giving a broad overview of related work from across the machine learning community and beyond. Then, we will focus on the algorithm configuration problem and how to solve it based on extensions of Bayesian optimization and bandits. We will also survey a wide range of other methods based on stochastic local search, algorithm portfolios, and more. Throughout, we will emphasize big picture ideas, motivational case studies, and core methodological innovations. We will conclude by surveying important open problems and exciting initial results from the broader community that offer potential ways forward.

Author Information

Kevin Leyton-Brown (University of British Columbia)

Kevin Leyton-Brown is a Professor of Computer Science at UBC and a Canada CIFAR AI Chair at Amii. He holds a PhD and M.Sc. from Stanford (2003; 2001) and a B.Sc. from McMaster (1998). He applies machine learning both to the design of heuristic algorithms and to the design and operation of electronic markets. He has co-written two books and over 100 peer-refereed technical articles. He was elected Fellow of the Association for the Advancement of Artificial Intelligence (AAAI) in 2017 and ACM Distinguished Member in 2018. With a team of 18 others, he was awarded the INFORMS Franz Edelman Award for Achievement in Operations Research and the Management Sciences, described as “the leading O.R. and analytics award.” He is the recipient of UBC's 2015 Charles A. McDowell Award for Excellence in Research, a 2014 NSERC E.W.R. Steacie Memorial Fellowship--previously given to a computer scientist only 10 times since its establishment in 1965--and a 2013 Outstanding Young Computer Science Researcher Prize from the Canadian Association of Computer Science. He is Chair of ACM SIGecom and has served as associate editor for top AI journals AIJ and JAIR. He co-taught two Coursera courses to over 750,000 students and has received multiple awards for teaching at UBC.

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.

More from the Same Authors