Fall 2021

Robustness in High-dimensional Statistics and Machine Learning

Today’s data pose unprecedented challenges to statisticians and data analysts. It may be incomplete, corrupted, or exposed to some unknown source of contamination. We need new methods and theories to grapple with these challenges. While the rich field of robust statistics addresses some of these questions, there are many new foundational challenges – both statistical and computational, that are posed by high-dimensional data. The goal is to explore several theoretical frameworks and directions towards designing estimators and learning algorithms that are tolerant to errors, contamination, and misspecification in data.

Organizers

• Aravindan Vijayaraghavan (Northwestern University)
• Chao Gao (University of Chicago)
• Yu Cheng (University of Illinois at Chicago) 

Workshops

• September 21: Kickoff event for Fall Special Quarter on “Robustness in high dimensional statistics and machine learning” Yu Cheng, Chao Gao and Aravindan Vijayaraghavan.
• October 19th (Tuesday): Mini-workshop on Statistical and Computational Aspects of Robustness in High-dimensional Estimation
• November 16th (Tuesday): Mini-workshop on New directions on Robustness in ML

Graduate Courses