Webcast Option: https://yale.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=db81893e-b646-4825-bfaf-b3d001549c96
Title: Algorithms for multi-group learning
Abstract: Multi-group learning is a formal learning criterion that is concerned with the conditional risks of predictors within subgroups of a population. The criterion addresses practical concerns such as subgroup fairness and hidden stratification. I’ll talk about the structure of solutions to the multi-group learning problem, as well as some simple and near-optimal algorithms for the learning problem.
This talk is based on a number of joint works with Navid Ardeshir, Siva Balakrishnan, Noah Bergam, Samuel Deng, Jingwen Liu, Chris Tosh, Lujing Zhang.
3:30pm - Pre-talk meet and greet teatime - 219 Prospect Street, 13 floor, there will be light snacks and beverages in the kitchen area. For more details and upcoming events visit our website at https://statistics.yale.edu/calendar.