Skip to main content
← Back to seminars

Past talk · AI/ML Seminar Series

The Measurement and Mismeasurement of Trustworthy ML

Sanmi Koyejo

Assistant Professor, Department of Computer Science, University of Illinois at Urbana-Champaign

Date & time
Monday, April 12, 2021 · 1:00 PM
Location
Online (live stream)

Abstract

Across healthcare, science, and engineering, we increasingly employ machine learning to automate decision-making that affects our lives in profound ways. However, ML can fail, and reliably measuring such failures is the first step toward building trustworthy learning machines. Consider algorithmic fairness, where widely-deployed fairness metrics can exacerbate group disparities and are often incompatible. Measurement is also crucial for robustness, particularly in federated learning with error-prone devices. Across ML applications, the dire consequences of mismeasurement are a recurring theme. This talk outlines emerging strategies for addressing the measurement gap in ML and how this impacts trustworthiness.

About the speaker

Sanmi (Oluwasanmi) Koyejo is an Assistant Professor in Computer Science at the University of Illinois at Urbana-Champaign, developing the principles and practice of trustworthy machine learning with applications to neuroscience and healthcare. He completed his Ph.D. at UT Austin and postdoctoral research at Stanford. His awards include a UAI best paper award, a Sloan Fellowship, and a Kavli Fellowship.