Machine Learning /Duolingo Seminar
- Remote Access Enabled - Zoom
- Virtual Presentation
- LILY HU
- Ph.D. Candidate
- Applied Mathemtics and Philosophy
- Harvard University
Fair Classification and Social Welfare," and "Do Causal Diagrams Assume a Can Opener?
This talk will be a double-feature. In the first half, I will discuss recent work with Yiling Chen connecting work in fair classification with some concepts in welfare economics. I take the connection to be rather natural: Now that machine learning algorithms lie at the center of many important resource allocation pipelines, computer scientists have been unwittingly cast as partial social planners. Given this state of affairs, important questions follow. How do leading notions of fairness as defined by computer scientists map onto longer-standing notions of social welfare? In this talk, I will present a welfare-based analysis of fair classification regimes. In the second half, I will discuss a topic that bridges algorithmic fairness and work in metaphysics and philosophy of science: recent attention to causal inference methods in sorting out when algorithms are discriminatory or unfair. Debate about what causal thinking gets right and what it gets wrong has been extensive both within fair ML and also outside of it. I will try to contribute some new points in these debates.
Lily Hu is a PhD candidate in Applied Mathematics and Philosophy at Harvard University. She works on topics in machine learning theory, algorithmic fairness, and philosophy of (social) science, and political philosophy. Her current work focuses on causal inference methodology in the social sciences and is especially interested in how various statistical frameworks treat and measure the "causal effect" of social categories such as race, and ultimately, how such methods are seen to back normative claims about racial discrimination and inequalities broadly. She holds an A.B. in Mathematics from Harvard College and taught English and Spanish history in Madrid on a Fulbright Fellowship. Her current work is supported by an NSF Graduate Research Fellowship and a fellowship from the Jain Family Institute.
The ML/Duolingo Seminar is generously supported by Duolingo.