CDML Seminar: Jacob Steinhardt: Designing Robust Learners
Date: Thursday, February 27, 2020
Time: 1:30 PM to 2:30 PM Note: all times are in the Eastern Time Zone
Location: Patil/Kiva G449
Event Type: Seminar
Host: Aleksander Madry
Contact: Deborah Goodwin, 617.324.7303, email@example.com
Speaker URL: None
TALK: CDML Seminar: Jacob Steinhardt: Designing Robust Learners
Abstract: Data can be corrupted in many ways: via outliers, measurement errors, failed sensors, batch effects, and so on. Standard maximum likelihood learning will either reproduce there errors or fail to converge entirely. Given this, what should we do instead? I will present a general framework for studying robustness to different families of errors in the data, and use this framework to provide guidance on designing error-robust estimators.
Created by Deborah Goodwin at Thursday, February 20, 2020 at 2:02 PM.