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.
Highlights
Machine learning is increasingly being used to inform sensitive decisions, including legal decisions such as whether to offer bail to a defendant [Lakkaraju et al 2017], and financial decisions such as whether to give a loan to an applicant [Hardt et al 2016]
Our goal is to verify whether a given fairness specification holds for a given machine learning model, focusing on specifications that have been proposed in the machine learning literature
We show the number of lines of code and some statistics about the rejection sampling approach we use to sample the population models
Summary
Machine learning is increasingly being used to inform sensitive decisions, including legal decisions such as whether to offer bail to a defendant [Lakkaraju et al 2017], and financial decisions such as whether to give a loan to an applicant [Hardt et al 2016]. In these settings, for both ethical and legal reasons, it is of paramount importance that decisions are made fairly and without discrimination [Barocas and Selbst 2016; Zarsky 2014]. Our goal is to verify whether a given fairness specification holds for a given machine learning model, focusing on specifications that have been proposed in the machine learning literature.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
