Online Learning and Bandit Problems with Applications to Revenue Management (Yuan Zhou)

Brief Introduction

1. Multi-armed Bandit Framework

2. The Upper Confidence Bound (UCB) Method

3. Elementary Improvements for Both Regret Minimization and Pure Exploration Settings

4. The Law-of-Iterated-Logarithm UCB Algorithm

5. Linear Contextual Bandits

6. Generalized Linear Models and Generalized Linear Contextual Bandits

7. Dynamic Assortment Optimization and the Multilinear Logit Bandit Problem

8. (If Time Permits) Zeroth Order Convex Optimization


2018-07-11 ~ 2018-08-05   


Yuan Zhou, Indiana University Bloomington


Room 104, School of Information Management & Engineering, Shanghai University of Finance & Economics

Application and Registration


Contact Us

Directions to ITCS

View Direction Page