The notion of bounded rationality originated from the insight that perfectly rational behavior cannot be realized by agents with limited cognitive or computational resources. Research on bounded rationality, mainly initiated by Herbert Simon, has a longstanding tradition in economics and the social sciences, but also plays a major role in modern AI and intelligent agent design. Taking actions under bounded resources requires an agent to reflect about how to use these resources in an optimal way -- hence, to reason and take decisions on a meta-level. In this talk, we will look at automated machine learning (AutoML) and related problems from the perspective of bounded rationality, essentially viewing an AutoML tool as an agent that has to train a model on a given set of data, and the search for a good way of doing so (a suitable “ML pipeline”') as deliberation on a meta-level.
Eyke Hüllermeier is a full professor at the Institute of Informatics at LMU Munich, where he heads the Chair of Artificial Intelligence and Machine Learning. He studied mathematics and business computing, received his PhD in computer science from Paderborn University in 1997, and a Habilitation degree in 2002. Prior to joining LMU, he spent two years as a Marie Curie fellow at the IRIT in Toulouse (France) and held professorships at the Universities of Dortmund, Magdeburg, Marburg, and Paderborn. His research interests are centered around methods and theoretical foundations of artificial intelligence, with a specific focus on machine learning and uncertainty in AI. He has published more than 300 articles on these topics in top-tier journals and major international conferences, and several of his contributions have been recognized with scientific awards. Professor Hüllermeier is an active member of the AI community, has organized several conferences and scientific events, and serves on the editorial board of various journals, including the Journal of Machine Learning Research, Machine Learning, Data Mining and Knowledge Discovery, and the International Journal of Approximate Reasoning.