【直播】【QuACT系列报告】阮雨霏:Linear Bandits with Limited Adaptivity and...
本系列报告由中国科学院计算技术研究所主办,于2021年6月1日10:00开始,授权蔻享学术进行网络直播。
直播二维码
Linear Bandits with Limited Adaptivity
and Learning Distributional Optimal Design
报告人
阮雨霏 (University of Illinois at Urbana-Champaign)
时间
2021年6月1日 10:00-11:00
Motivated by practical needs such as large-scale learning, we study the impact of adaptivity constraints to linear contextual bandits, a central problem in online learning and decision making. Unlike traditional online learning problem which has full adaptivity at a per-time-step scale, our work focuses on the model in which the learning process is executed in parallelization but still wants to achieve optimal performance. In this talk, I will show that in such batch learning model, only batches are needed to achieve the optimal regret. Along the way in the proof, I will introduce the distributional optimal design, which is a natural extension of the optimal experiment design in statistical learning, and introduce our statistically and computationally efficient learning algorithm for the problem, which may be of independent interest.This is joint work with Jiaqi Yang and Yuan Zhou.
报告人简介
Yufei Ruan is a third year Ph.D. student in Industrial & Enterprise Systems Engineering from University of Illinois at Urbana-Champaign. Her research focuses on the theoretical part of machine learning, especially on online learning and reinforcement learning. She completed her undergraduate studies in Mathematics at Tsinghua University.
编辑:王茹茹
往期回顾
欢迎大家提供各类学术会议或学术报告信息,以便广大科研人员参与交流学习。