Probabilistic verification of fairness properties via concentration
Name
3360544.pdf
Description
Published version
Size
504.25 KB
Format
Adobe PDF
Checksum (MD5)
ceb2eb67f1834b215fd636872e12b43a
Author(s)
Bastani, Osbert
Zhang, Xin
Solar-Lezama, Armando
Date Issued
2019
Journal
Proceedings of the ACM on Programming Languages
Publisher
Association for Computing Machinery (ACM)
Version
Final published version
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.
MIT Department
Massachusetts Institute of Technology. Institute for Data, Systems, and Society
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution 4.0 International license
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3360544
