RAIN Seminar: Biases Beyond Observation, Moritz Hardt, University of California, Berkeley

RAIN Seminar<br><br>Title: Biases Beyond Observation<br>Speaker: Moritz Hardt, University of California, Berkeley<br>Date: November 1, 2017<br>Time: 12:00pm<br>Location: Y2E2 101<br><br>If you would like to meet with him, please sign up in the following document: <a href="https://docs.google.com/spreadsheets/d/1SsLACzqffhtuozL2PHlFR9iK0nM_G6F6... <br><br><br>Abstract: <br>Most proposed fairness measures for machine learning are observational: They depend only on the joint distribution of the features, predictor, and outcome. I will highlight a few useful observational criteria, before arguing why observational criteria in general are unable to resolve questions of fairness conclusively. Moving beyond observational criteria, I will outline a causal framework for reasoning about discrimination based on sensitive characteristics. <br><br>Bio: <br>Moritz Hardt is an Assistant Professor in the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley. After obtaining a PhD in Computer Science from Princeton University in 2011, he was a postdoctoral scholar and research staff member at IBM Research Almaden, followed by two years as a research scientist at Google Research and Google Brain. Hardt’s research aims to make the practice of machine learning more robust, reliable, and aligned with societal values.<br>

Date: 
Wednesday, November 1, 2017 - 12:00pm to 1:00pm
location: 
Jerry Yang and Akiko Yamazaki Environment and Energy Building (Y2E2), 473 Via Ortega, Stanford, CA 94305, USA