Probabilistic verification of fairness properties via concentration

Abstract

As machine learning systems are increasingly used to make real world legal and financial decisions, it is of paramount importance that we develop algorithms to verify that these systems do not discriminate against minorities. We design a scalable algorithm for verifying fairness specifications. Our algorithm obtains strong correctness guarantees based on adaptive concentration inequalities; such inequalities enable our algorithm to adaptively take samples until it has enough data to make a decision. We implement our algorithm in a tool called VeriFair, and show that it scales to large machine learning models, including a deep recurrent neural network that is more than five orders of magnitude larger than the largest previously-verified neural network. While our technique only gives probabilistic guarantees due to the use of random samples, we show that we can choose the probability of error to be extremely small.

Document Details

Document Type
Pub Defense Publication
Publication Date
Oct 10, 2019
Source ID
10.1145/3360544

Entities

People

  • Armando Solar-lezama
  • Osbert Bastani
  • Xin Zhang

Organizations

  • Massachusetts Institute of Technology
  • Office of Naval Research
  • University of Pennsylvania

Tags

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Applied Combinatorial Optimization and Logic Circuit Design.
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks