Minimax optimal testing by classification
Speaker: Lucas Kania
Abstract: We will introduce the minimax framework for hypothesis testing, some basic tricks of the trade, and discuss the paper "Minimax optimal testing by classification" by Gerber, Han, and Polyanskiy [1]. In this work, the authors study the effectiveness of learned classifiers for deciding if two distributions are equal or far apart in the total variation distance. We aim to make the presentation self-contained; hence, no previous knowledge about minimax hypothesis testing will be assumed. [1] https://proceedings.mlr.press/v195/gerber23a.html