I am a Computer Science PhD candidate at Brown University where I am fortunate to be advised by Suresh Venkatasubramanian. I am interested in the process of analyzing machine learning systems to determine if they are fair, ethical, or legal; my research examines this process from an interdisciplinary perspective. My ultimate goal is to inform the development of law and policy to prevent the intentional or unintentional deployment of harmful data-driven technology. My research has been supported by Arthur AI and the ARCS Foundation. I’m also an affiliate of Brown’s new Center for Technological Responsibility, Reimagination and Redesign.
Before my advisor and I joined Brown in 2021, I spent the first two years of my PhD at the University of Utah. Previously, I developed actuarial risk models on the Data Science team at MassMutual while completing my M.S. in Computer Science at the University of Massachusetts. I received my B.A. in Mathematics from Scripps College in 2016.
cv: here (updated April 2022)
email: iekumar at brown dot edu
office: Data Science Initiative, 164 Angell Floor 3
Peer-Reviewed Conference Publications
Equal credit opportunity in algorithms: Aligning algorithmic fairness research with U.S. fair lending regulation.
I. Elizabeth Kumar, Keegan Hines, John P. Dickerson.
In Proceedings of the 5th AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES), 2022.
The fallacy of AI functionality.
Inioluwa Deborah Raji*, I. Elizabeth Kumar*, Aaron Horowitz, Andrew D. Selbst.
In Proceedings of the 5th ACM Conference on Fairness, Accountability, and Transparency (FAccT), 2022.
Shapley Residuals: Quantifying the limits of the Shapley value for explanations.
I. Elizabeth Kumar, Carlos Scheidegger, Suresh Venkatasubramanian, Sorelle Friedler.
In Advances in Neural Information Processing Systems 34 (NeurIPS), 2021.
Epistemic values in feature importance methods: Lessons from feminist epistemology.
Leif Hancox-Li*, I. Elizabeth Kumar*.
In Proceedings of the 4th ACM Conference on Fairness, Accountability, and Transparency (FAccT), 2021.
Best Paper Award.
Problems with Shapley-value-based explanations as feature importance measures.
I. Elizabeth Kumar, Suresh Venkatasubramanian, Carlos Scheidegger, Sorelle Friedler.
In Proceedings of the 37th International Conference on Machine Learning (ICML), 2020.
The Legal Construction of Black Boxes.
Andrew D. Selbst, Suresh Venkatasubramanian, I. Elizabeth Kumar.
Drafts presented at PLSC 2021, WeRobot 2021.