Dissertation 'Bounds and Applications of Concentration of Measure in Fair Machine Learning and Data Science' received the Joukowsky Outstanding Dissertation Prize. Awarded Dean's Faculty Fellowship as a visiting assistant professor at Brown University and CDS Postdoctoral Fellowship at the University of Massachusetts Amherst.
Research Experience
Currently a postdoctoral scholar at Duke and Carnegie Mellon Universities, working with Professors Walter Sinnott-Armstrong, Jana Schaich Borg, Vincent Conitzer, and Hoda Heidari. Formerly a visiting assistant professor at Brown University.
Education
Ph.D. from Brown University under the supervision of Eli Upfal; B.S. in Computer Science, Mathematics, and Biology from Tufts University.
Background
Research interests include problems involving sampling, randomization, and learning in data science, with a particular focus on uniform convergence theory and the rigorous treatment of fair machine learning. Specializes in theoretical bounds on generalization error in exotic settings and applies such bounds to real-world tasks, notably in data science, empirical game theory, and fair machine learning.
Miscellany
Favorite theorem is the Dvoretzky-Kiefer-Wolfowitz Inequality, and favorite algorithm is simulated annealing.