Title: Online “Safe” Learning and Decision Making
Abstract: Data-driven learning and decision-making in complex systems are often subject to a variety of operational constraints such as safety, fairness, and budget constraints. The problem becomes particularly challenging when the constraints are unknown, sometimes adversarial, and must be learned while making decisions. This talk presents several recent results on this topic and explains the important roles of optimism, pessimism, and queue in online safe learning and decision-making.
Bio: Lei Ying is currently a Professor at the Electrical Engineering and Computer Science Department of the University of Michigan, Ann Arbor. His research is broadly in the interplay of complex stochastic systems and big data, including reinforcement learning, large-scale communication/computing systems for big-data processing, private data marketplaces, and large-scale graph mining.