Associate Professor of Electrical Engineering and Computer Science
Pennsylvania State University
Seminar: Stochastic Linear Contextual Bandits with Diverse Contexts
Abstract: In this talk, we investigate the impact of context diversity on stochastic linear contextual bandits. As opposed to the previous view that contexts lead to more difficult bandit learning, we show that when the contexts are sufficiently diverse, the learner is able to utilize the information obtained during exploitation to shorten the exploration process, thus achieving reduced regret. We design the LinUCB-d algorithm, and propose a novel approach to analyze its regret performance. The main theoretical result is that under the diverse context assumption, the cumulative expected regret of LinUCB-d is bounded by a constant. As a by-product, our results improve the previous understanding of LinUCB and strengthen its performance guarantee.
About the Speaker: Dr. Jing Yang is an associate professor in the Department of Electrical Engineering at Pennsylvania State University. She received her MS and PhD degrees from the University of Maryland, College Park, and the BS degree from the University of Science and Technology of China, all in electrical engineering. She received the National Science Foundation CAREER award in 2015 and the WICE Early Achievement Award in 2020, and was selected as one of the 2020 N2Women: Stars in Computer Networking and Communications. She has served as a Symposium/Workshop Co-chair for ICC 2021, INFOCOM 2021-AoI Workshop, WCSP 2019, CTW 2015, PIMRC 2014, a TPC Member of several conferences, and an Editor for IEEE Trans. on Wireless Communications and IEEE Trans. on Green Communications and Networking. Her research interests lie in wireless communications and networking, machine learning theory, and information theory.
Host: Cong Shen, assistant professor, electrical and computer engineering