CDML Seminar: Jacob Steinhardt: Designing Robust Learners

Speaker: Jacob Steinhardt

Date: Thursday, February 27, 2020

Time: 1:30 PM to 2:30 PM Note: all times are in the Eastern Time Zone

Public: Yes

Location: Patil/Kiva G449

Event Type: Seminar

Room Description:

Host: Aleksander Madry

Contact: Deborah Goodwin, 617.324.7303, dlehto@csail.mit.edu

Relevant URL:

Speaker URL: None

Speaker Photo:
Photo

Reminders to: seminars@csail.mit.edu

Reminder Subject: 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.

Research Areas:

Impact Areas:

This event is not part of a series.

Created by Deborah Goodwin Email at Thursday, February 20, 2020 at 2:02 PM.