Multi-Armed Bandits: History, Theory, and Applications
Friday, October 15, Giedt Hall 1003, 12:00pm-1:00pm
The first Multi-Armed Bandit (MAB) problem was posed by Thompson in 1933 for the application of clinical trial. Since then, MAB has developed into an important branch in stochastic optimization and machine learning and has found a wide range of applications including multi-agent systems, web search and Internet advertising, social networks, and queueing systems. It has recently received increasing attention from the communications and networking research community with its applications in dynamic systems and cognitive radio networks. This talk covers the history, classic and recent results, and open problems in MAB and restless MAB with an emphasis on applications in wireless communications and networking.
Qing Zhao received the Ph.D. degree in Electrical Engineering in 2001 from Cornell University, Ithaca, NY. In August 2004, she joined the Department of Electrical and Computer Engineering at UC Davis where she is currently an Associate Professor. Her research interests are in the general area of dynamic systems, communication networks, and stochastic optimization. She received the 2000 Young Author Best Paper Award from IEEE Signal Processing Society and the 2008 Outstanding Junior Faculty Award from the UC Davis College of Engineering. She has been named a UC Davis Chancellor's Fellow in 2010 and will hold the title from 2010 to 2015. She is also a co-author of two student paper awards at IEEE ICASSP 2006 and IEEE Asilomar Conference 2006.