topics: algorithmic fairness, machine learning, differential privacy


Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness

  • Preprint. November 2017.

Accuracy First: Selecting a Differential Privacy Level for Accuracy Constrained ERM

  • Neural Information Processing Systems [NIPS  2017]
  • Theory and Practice of Differential Privacy [TPDP 2017]

A Framework for Meritocratic Fairness of Online Linear Models

A Convex Framework for Fair Regression

  • Fairness Accountability and Transparency in Machine Learning [FATML  2017]

Fairness in Linear Bandit Problems

  • Fairness Accountability and Transparency in Machine Learning [FATML 2016]
  • One of 4 spotlight talks given at NYU Law School, November 2016.

Aztec Castles and the dP3 Quiver

  • The Journal of Physics A: Mathematical and Theoretical [J. Phys. A 2015]

Mahalanobis Matching and Equal Percent Bias Reduction

  • Senior Honors Thesis [Harvard University 2015]

Plane Partitions and Domino Tilings

  • Intel Science Talent Search Semifinalist [ISTS 2011]
  • A new bijection between domino tilings of aztec diamonds and plane partitions is developed, leading to a simple proof of the generating function. A purely combinatorial proof of the Aztec Diamond Theorem due to [EKLP] is given. PDF available upon request.