讲座题目：

Learning & Control in Safety-Critical Systems

讲座时间：

2022年6月22日周三10:00-11:30am北京时间

主持人：

宋洁教授、副院长

北京大学工学院 工业工程与管理系

开讲者：

Adam Wierman

Professor of Computing and Mathematical Sciences

Director of Information Science and Technology

California Institute of Technology

开讲学者简介

Peking University ES Seminars

Adam Wierman is a Professor in the Department of Computing and Mathematical Sciences at Caltech. He received his Ph.D., M.Sc., and B.Sc. in Computer Science from Carnegie Mellon University and has been a faculty at Caltech since 2007. Adam’s research strives to make the networked systems that govern our world sustainable and resilient. He is best known for his work spearheading the design of algorithms for sustainable data centers and his co-authored book “The Fundamentals of Heavy-tails”. He is a recipient of multiple awards, including the ACM Sigmetrics Rising Star award, the ACM Sigmetrics Test of Time award, the IEEE Communications Society William R. Bennett Prize, multiple teaching awards, and is a co-author of papers that have received “best paper” awards at a wide variety of conferences across computer science, power engineering, and operations research.

讲座摘要

Peking University ES Seminars

Making use of modern black-box AI tools such as deep reinforcement learning is potentially transformational for safety-critical systems such as data centers, the electricity grid, transportation, and beyond. However, such machine-learned algorithms typically do not have formal guarantees on their worst-case performance, stability, or safety and are typically difficult to make use of in distributed, networked settings. So, while their performance may improve upon traditional approaches in “typical” cases, they may perform arbitrarily worse in scenarios where the training examples are not representative due to, e.g., distribution shift or unrepresentative training data, or in situations where global information is unavailable to local controllers. These represent significant drawbacks when considering the use of AI tools in safety-critical networked systems. Thus, a challenging open question emerges: Is it possible to provide guarantees that allow black-box AI tools to be used in safety-critical applications? In this talk, I will provide an overview of a variety of projects from my lab at Caltech that seek to develop robust and localizable tools combining model-free and model-based approaches to yield AI tools with formal guarantees on performance, stability, safety, and sample complexity.