Research

Privacy | Fairness | Machine Learning

All author ordering is strictly alphabetical. My research has a few threads:

  1. The study of fundamental problems in data privacy, with an emphasis on private machine learning. This includes differential privacy and differentially private learning, machine unlearning, and the study of attacks against machine learning models such as membership inference.
  2. Adaptive Data Analysis
  3. Fairness in Machine Learning (design of new algorithms and fairness notions, in the online, bandit, batch settings) and connections to model interpretability.

Preprints

19. Private Regression in Multiple Outcomes (PRIMO) [TPDP@ICML ’22]

18. On the Privacy Risks of Algorithmic Recourse [arXiv]

Publications

17. Adaptive Machine Unlearning [NEURIPS ’21]

16. Eliciting and Enforcing Subjective Individual Fairness [FORC ’21]

15. Descent-to-Delete: Gradient-Based Methods for Machine Unlearning [Algorithmic Learning Theory ’21] Code

14. Optimal, Truthful, and Private Securities Lending [ACM AI in Finance ’20, NEURIPS Workshop on Robust AI in Financial Services ’19] selected for oral presentation!

13. Differentially Private Objective Perturbation: Beyond Smoothness and Convexity [ICML ’20, NEURIPS Workshop on Privacy in ML ’19]

12. A New Analysis of Differential Privacy’s Generalization Guarantees [ITCS ’20] regular talk slot!

11. The Role of Interactivity in Local Differential Privacy  [FOCS ’19]

10. How to use Heuristics for Differential Privacy  [FOCS ’19] Video.

9. An Empirical Study of Rich Subgroup Fairness for Machine Learning [ACM FAT* ’19, ML track]

  • Led development on package integrated into the IBM AI Fairness 360 package here. AIF360 development branch on my Github, with a stand-alone package developed by the AlgoWatch Team.

8. Fair Algorithms for Learning in Allocation Problems [ACM FAT* ’19, ML track]

7. Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness [ICML ’18, EC MD4SG ’18]

6. Mitigating Bias in Adaptive Data Gathering via Differential Privacy [ICML ’18]

5. Accuracy First: Selecting a Differential Privacy Level for Accuracy Constrained ERM [NIPS ’17, Journal of Privacy and Confidentiality ’19]

4. A Framework for Meritocratic Fairness of Online Linear Models  [AAAI/AIES ’18]

3. Rawlsian Fairness for Machine Learning [FATML ’16]

2.  A Convex Framework for Fair Regression  [FATML ’17]

Math stuff from College & High School

1. Aztec Castles and the dP3 Quiver [Journal of Physics A ’15]

0. Mahalanobis Matching and Equal Percent Bias Reduction[Senior Thesis, Harvard ’15]

0. Plane Partitions and Domino Tilings [Intel Science Talent Search Semifinalist, ’11]