Colloquium - Machine Teaching: Optimal Control of Machine Learning

October 12, 2018 - 4:00pm
40 SH
Jerry Zhu
University of Wisconsin-Madison | Computer Sciences

As machine learning is increasingly adopted in science and engineering, it becomes important to take a higher level view where the machine learner is only one of the agents in a multi-agent system.  Other agents may have an incentive to control the learner.  As examples, in adversarial machine learning an attacker can poison the training data to manipulate the model the learner learns; in education a teacher can optimize the curriculum to enhance student (modeled as a computational learning algorithm) performance.  Machine teaching is optimal control theory applied to machine learning: the plant is the learner, the state is the learned model, and the control is the training data.  In this talk I survey the mathematical foundation of machine teaching and the new research frontiers opened up by this confluence of machine learning and control theory.

BioJerry Zhu Portrait from

Jerry Zhu is the Sheldon & Marianne Lubar Professor in the Department of Computer Sciences at the University of Wisconsin-Madison. His research focuses on machine learning.  Jerry received his Ph.D. from Carnegie Mellon University in 2005. He is a recipient of a National Science Foundation CAREER Award in 2010 and ICML classic paper prize in 2013. He is co-chair for CogSci 2018 and AISTATS 2017.