Bio
Jian Li is currently an assistant professor at Institute for Interdisciplinary Information Sciences (IIIS, previously ITCS), Tsinghua University,
headed by Prof. Andrew Yao. He got his BSc degree from Sun Yat-sen (Zhongshan) University, China, MSc degree in computer science
from Fudan University, China and PhD degree in the University of Maryland, USA. His major research interests lie in the broad area
of theoretical computer science, machine learning and databases. He co-authored several research papers that have been published in
major computer science conferences and journals. He received the best paper awards at VLDB 2009 and ESA 2010. He is also a recipient
of the "221 Basic Research Plan for Young Faculties" at Tsinghua University and the "new century excellent talents award" by Ministry
of Education of China.
Talk Information
Multi-armed Bandits,Online Learning and Sequential Prediction2016/09/06 2:00 to 3:00pmECE Conference Room, MEB 3237
AbstractOnline learning (or sequential prediction) has been a very active research area in
machine learning. I will give a very brief introduction to online learning.
Then, I will focus on a very popular model in online learning, the stochastic multi-armed bandit model,
and present some of our recent theoretical results on combinatorial bandits and the pure-exploration
multi-armed bandit problems. If time permits, I will also talk about some practical
projects our group has done on online and sequential prediction in traffic related applications -- including
a deep learning based prediction algorithm, which won the 2nd place (among 1650 teams all over the world)
and the most potential award in Didi (China's version of Uber) taxi supply-demand prediction
competition.