Using Deep Adversarial Learning To Construct Optimal Statistical Procedures

Date: 
April 7, 2021
Time: 
3:00 - 4:00pm
Place: 
Zoom - Registry Link Below

Traditionally, statistical procedures have been derived via analytic calculations whose validity often relies on sample size growing to infinity. Dr. Luedtke will describe an approach that uses deep adversarial learning to numerically construct statistical procedures that perform well even in small samples.