A Central Limit Theorem, Loss Aversion and Multi-Armed Bandit
报告题目(Title)：A Central Limit Theorem, Loss Aversion and Multi-Armed Bandit
报告人(Speaker)：陈增敬 教授 (山东大学)
地点(Place)：后主楼 1220
时间(Time)：2021年8月28日, 10:30-11:30
邀请人(Inviter)：何辉
报告摘要
We establish a central limit theorem under the assumption that
conditional variances can vary in a largely unstructured history-dependent
way across experiments subject only to the restriction that they lie in a fixed
interval. Limits take a novel and tractable form, and are expressed in terms
of oscillating Brownian motion. A second contribution is application of this
result to a class of multi-armed bandit problems where the decision-maker
is loss averse. The talk is based on a joint work with Larry G. Epstein and
Guodong Zhang.
