您现在的位置: 实验室首页 >> 最新动态 >> 学术报告 >> 关于美国加州理工学院眭亚南博士学术报告的通知
关于美国加州理工学院眭亚南博士学术报告的通知

报告时间:2017年9月14日(周四)下午14:00
报告地点:浙江大学紫金港校区蒙民伟楼402会议室
报告主题:Bandit Problems with Preference Feedback, Structured Decision Spaces, and Safety Constraints
报告人:Yanan Sui 博士

AbstractBandit algorithms tackle the fundamental challenge of balancing exploration (collecting data for learning better models) and exploitation (using the estimates to make decisions). In this talk, I will formalize bandit problems with preference feedback (Is "A" better than "B"?), with structured decision spaces (a large set of arms that are correlated), and with safety concerns (when bad samples are not allowed). These constraints commonly exist in many applications. In particular, we are motivated by online decision-making for clinical treatment and robotic control. This talk will exhibit several algorithms for these constrained bandit problems. The theoretical guarantees and empirical efficiencies of our algorithms will be presented. I will also show some of our clinical results -- online decision-making for spinal cord injury therapy.

BioYanan Sui is a postdoc researcher in Computing and Mathematical Sciences department at California Institute of Technology. He got his PhD degree at Caltech in Computation and Neural Systems (with minor in Applied and Computational Mathematics). Yanan received his Bachelor's Degree from Tsinghua University. His research interests are machine learning, neural engineering and robotics. He is currently working on theories for online learning with human in the loop and applications on neural rehabilitation and robotics.

http://www.its.caltech.edu/~ysui/

 

[时间:2017-09-13 15:26 点击: 次]
地址:中国·浙江·杭州·余杭塘路866号(310058)
Copyright © 浙江大学CAD&CG国家重点实验室 浙ICP备05074421