The Ohio State University
Seminar: Model-Agnostic Meta-Learning Based on Optimization Theory
Abstract: Meta-learning or learning to learn has been shown to be a powerful tool for fast learning over unseen tasks by efficiently extracting the knowledge from a range of observed tasks. Such empirical success thus highly motivates theoretical understanding of the performance guarantee of meta-learning, which will serve to guide the better design of meta-learning and further expand its applicability. In this talk, I will present our recent studies of meta-learning based on optimization theory. Specifically, I will present our characterization of the convergence guarantee and computational complexity for a few meta-learning approaches that have been widely used in practice, including model-agnostic meta-learning (MAML), a more scalable variant of MAML called the almost no inner loop, and bi-level meta-learning. I will also present our recent design of faster algorithms for meta-learning. I will finally present the experimental validations of our theoretical findings and discuss a few future directions on the topic. The work presented was jointly conducted with Dr. Kaiyi Ji (U. Michigan), Daouda Sow (OSU), Junjie Yang (OSU), Dr. Jason Lee (Princeton), and Dr. Vincent Poor (Princeton).
About the Speaker: Dr. Yingbin Liang is a professor at the Department of Electrical and Computer Engineering at the Ohio State University and a core faculty of the Ohio State Translational Data Analytics Institute. She also serves as deputy director of the AI-Edge Institute at OSU. Dr. Liang earned her Ph.D. in electrical engineering from the University of Illinois at Urbana-Champaign in 2005 and served on the faculty of University of Hawaii and Syracuse University before she joined OSU. Dr. Liang's research interests include machine learning, optimization, information theory and statistical signal processing. Dr. Liang earned the National Science Foundation CAREER Award and the State of Hawaii Governor Innovation Award in 2009. She also earned a EURASIP Best Paper Award in 2014.
Host: Cong Shen, assistant professor of electrical and computer engineering