Research
What the work is about. The full record is on the papers page.
Algorithmic Fairness and Accountability
Formal methods for auditing automated decision systems, and the policy frameworks that determine whether those audits carry any weight.
- Auditing Automated Decision Systems Without Access to the ModelACM FAccT, 2026
- On the Limits of Statistical Parity as a Governance StandardNeurIPS, 2025
- The Measurement Gap in Algorithmic HarmACM FAccT, 2024
- Fairness Constraints Under Distribution ShiftICML, 2022
- A Geometric View of Group FairnessSIAM Journal on Computing, 2021
Governance of Automated Decisions
What regulators can require, what they can verify, and the distance between the two.
- Auditing Automated Decision Systems Without Access to the ModelACM FAccT, 2026
- On the Limits of Statistical Parity as a Governance StandardNeurIPS, 2025
- What Regulators Can Verify: A Formal Account of Algorithmic DisclosureJournal of Privacy and Confidentiality, 2025
- Toward Enforceable Standards for Automated Decision SystemsCenter for Tech Responsibility, 2023
- Fairness and Abstraction in Sociotechnical SystemsACM FAccT, 2019
Computational Geometry
Structure and approximation in high-dimensional data, the thread running back to the beginning of my work.
- Certifying Robustness in High-Dimensional ClassificationICML, 2024
- A Geometric View of Group FairnessSIAM Journal on Computing, 2021
- Approximation Algorithms for Streaming Geometric DataSODA, 2011
- On Bregman Divergences and ClusteringJournal of Machine Learning Research, 2008
- Shape Matching in High DimensionsSymposium on Computational Geometry, 2004