Professor, Department of Electrical and Computer Engineering
Deputy Director, AI-Edge Institute
Core Faculty, Translational Data Analytics Institute (TDAI)
The Ohio State University
Office: DL 606
Email: liang.889@osu.edu
Google Scholar Profile
Multiple PhD (available in Fall 2024) and Postdoc Positions (available immediately)
Dr. Yingbin Liang 's lab will have multiple PhD positions (supported by research assistantship) starting in Fall 2024. Her lab also has postdoc positions available immediately. All positions are in the areas of Machine Learning, Deep Learning, and Large-scale Optimization. Students and postdocs working with her will also be affiliated with the NSF AI Institute for Future Edge Networks and Distributed Intelligence (AI-EDGE) and will have opportunities to collaborate with the faculty in the institute.
Short Biography
Dr. Yingbin Liang is currently a Professor at the Department of Electrical and Computer Engineering at the Ohio State University (OSU), and a core faculty of the Ohio State Translational Data Analytics Institute (TDAI). She also serves as the Deputy Director of the AI-EDGE Institute at OSU. She received the Ph.D. degree 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, statistical signal processing, information theory, and wireless communications. Dr. Liang received the National Science Foundation CAREER Award in 2009, and the State of Hawaii Governor Innovation Award in 2009. Her paper received EURASIP Best Paper Award in 2014. She is currently serving as an Associate Editor for IEEE Transactions on Information Theory. She is an IEEE fellow.
Research Interests
My research spans over multiple disciplines including machine learning, large-scale optimization, information theory, and statistical signal processing, with the focused on the following directions:
Machine Learning and Deep Learning: We strive to develop fundamental theory on modern machine learning approaches, encompassing various aspects such as their underlying working mechanisms, generalization performance, and computational complexity. Our focus extends to topics such as language models, diffusion models, meta-learning, continual learning, adversarial machine learning, and more.
Reinforcement Learning: Our aim is to develop innovative algorithms that address the challenging issues prevalent in reinforcement learning, and characterize the statistical and computational complexity of these algorithms. These include handling nonstationarity, unknown reward, offline and off-policy data, partial observability, and accommodating soft and instantaneous hard constraints.
Large-scale Optimization: Our research is dedicated to creating cutting-edge and scalable algorithms for solving complex large-scale optimization problems. These problems often arise from modern data-driven machine learning applications. We emphasize the characterization of convergence rates and computational complexity of these algorithms. Some of our recent efforts revolve around bilevel optimization, distributionally robust optimization (DRO), and minimax optimization.
Information Theory and Communications: We are actively involved in the development of novel communication techniques, particularly those driven by emerging AI and machine learning advancements. Through the integration of learning theory, statistics, and information theory, we aim to characterize the performance of these techniques under wireless fading environments.
Honors and Awards
2014 EURASIP Best Paper Award for the EURASIP Journal on Wireless Communications and Networking
National Science Foundation CAREER Award, 2009
State of Hawaii Governor Innovation Award, 2009
M. E. Van Valkenburg Graduate Research Award, University of Illinois, 2005
Vodafone-US Foundation Fellows Initiative Research Merit Award, 2005
Vodafone-US Foundation Graduate Fellowship, 2003-2005