Many problems in science and engineering require estimating and optimizing an unknown function that is accessible only through noisy experiments. A central challenge here is the exploration—exploitation dilemma: Designing experiments that are informative for learning about the unknown objective, while focusing exploration where we expect high performance. The field of Bayesian optimization seeks to address these challenges by quantifying uncertainty about the unknown objective and utilizing the uncertainty to navigate the exploration—exploitation dilemma.

In this talk, Andreas Krause presents recent work motivated by key challenges in complex applications such as protein design. In particular, Krause discusses meta-learning of probabilistic models to share data from related tasks, directing exploration in combinatorial search spaces via reinforcement learning and exploiting causal structure to improve both sample efficiency and interpretability.

Bio:
Andreas Krause is a Professor of Computer Science at ETH Zurich, where he leads the Learning & Adaptive Systems Group and serves as Academic Co-Director of the Swiss Data Science Center and Chair of the ETH AI Center. Before that he was an Assistant Professor of Computer Science at Caltech and received his Ph.D. in Computer Science from Carnegie Mellon University and his Diplom in Computer Science and Mathematics from the Technical University of Munich. He is a Max Planck Fellow at the Max Planck Institute for Intelligent Systems, ACM Fellow and ELLIS Fellow, received the Roessler Prize, ERC Starting and Consolidator grants, Test of Time awards at KDD 2019 and ICML 2020 as well as the ETH Golden Owl teaching award. He served as Program Co-Chair for ICML 2018, General Chair for ICML 2023 and Action Editor for the Journal of Machine Learning Research. In 2023, he was appointed to the United Nations’ High-level Advisory Body on AI.

Find out more about The Institute for Experiential AI: https://ai.northeastern.edu/

Connect with us on
LinkedIn:   / eai-nu  
Facebook:   / experientialai  
X: https://x.com/Experiential_AI