• Publications
  • Influence
Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
The most prevalent notions of fairness in machine learning are statistical definitions: they fix a small collection of pre-defined groups, and then ask for parity of the classifier across these groups. Expand
Privacy-Preserving Generative Deep Neural Networks Support Clinical Data Sharing
Supplemental Digital Content is available in the text.
Fair Regression: Quantitative Definitions and Reduction-based Algorithms
We study the prediction of a real-valued target, such as risk score or recidivism rate, while guaranteeing a quantitative notion of fairness with respect to a protected attribute such as gender or race. Expand
Watch and learn: optimizing from revealed preferences feedback
A Stackelberg game is played between a leader and a follower. Expand
Adaptive Learning with Robust Generalization Guarantees
The traditional notion of generalization---i.e., learning a hypothesis whose empirical error is close to its true error---is surprisingly brittle. Expand
Strategic Classification from Revealed Preferences
We study an online linear classification problem in which the data is generated by strategic agents who manipulate their features in an effort to change the classification outcome. Expand
Dual Query: Practical Private Query Release for High Dimensional Data
We present a practical, differentially private algorithm for answering a large number of queries on high dimensional datasets. Expand
A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem
We present a smoothed analysis, showing that even when contexts may be chosen by an adversary, small perturbations of the adversary's choices suffice for the algorithm to achieve "no regret", perhaps (depending on the specifics of the setting). Expand
Orthogonal Random Forest for Causal Inference
We propose the orthogonal random forest, an algorithm that combines Neyman-orthogonality to reduce sensitivity with respect to estimation error of nuisance parameters with generalized random forests (Athey et al., 2017)--a flexible non-parametric method for statistical estimation of conditional moment models. Expand
Semiparametric Contextual Bandits
This paper studies semiparametric contextual bandits, a generalization of the linear stochastic bandit problem where the reward for an action is modeled as a linear function of known action features confounded by an non-linear action-independent term. Expand