• Publications
  • Influence
Fairness through awareness
TLDR
We study fairness in classification, where the goal is to prevent discrimination against individuals based on their membership in some group, while maintaining utility for the classifier (the university). Expand
  • 1,172
  • 152
  • PDF
Learning Fair Representations
TLDR
We propose a learning algorithm for fair classification that achieves both group fairness (the proportion of members in a protected group receiving positive classification is identical to the proportion in the population as a whole), and individual fairness (similar individuals should be treated similarly). Expand
  • 731
  • 73
  • PDF
Differential privacy under continual observation
TLDR
Differential privacy is a recent notion of privacy tailored to privacy-preserving data analysis [11]. Expand
  • 447
  • 63
  • PDF
Learning Adversarially Fair and Transferable Representations
TLDR
We propose and explore methods of learning adversarially fair representations. Expand
  • 201
  • 39
  • PDF
Preserving Statistical Validity in Adaptive Data Analysis
TLDR
We propose a principled study of how to guarantee the validity of statistical inference in adaptive data analysis. Expand
  • 249
  • 29
  • PDF
Combining Component Caching and Clause Learning for Effective Model Counting
TLDR
We integrate component caching with clause learning, one of the most important ideas used in modern SAT solvers, and show how this combination can be achieved so as to obtain the performance improvements just mentioned. Expand
  • 215
  • 26
  • PDF
Generalization in Adaptive Data Analysis and Holdout Reuse
TLDR
We give an algorithm that enables the validation of a large number of adaptively chosen hypotheses, while provably avoiding overfitting to the holdout set. Expand
  • 146
  • 24
  • PDF
Solving #SAT and Bayesian Inference with Backtracking Search
TLDR
Inference in Bayes Nets (BAYES) is an important problem with numerous applications in probabilistic reasoning. Expand
  • 77
  • 18
  • PDF
The reusable holdout: Preserving validity in adaptive data analysis
TLDR
We demonstrate a new approach for addressing the challenges of adaptivity based on insights from privacy-preserving data analysis based on ideas drawn from differential privacy. Expand
  • 233
  • 16
  • PDF
Stochastic Boolean Satisfiability
TLDR
This paper examines a generic stochastic satisfiability problem, SSAT, which can function for probabilistic domains as SAT does. Expand
  • 152
  • 16