Fast & Fair: Efficient Second-Order Robust Optimization for Fairness in Machine Learning
This addresses fairness issues in machine learning that can lead to harmful outcomes, such as demographic bias in facial recognition, but the approach is incremental as it builds on existing adversarial training techniques.
The paper tackles bias in deep neural networks related to sensitive attributes like race and gender by proposing a robust optimization problem, achieving improved fairness on synthetic and real-world datasets using an affine linear model.
This project explores adversarial training techniques to develop fairer Deep Neural Networks (DNNs) to mitigate the inherent bias they are known to exhibit. DNNs are susceptible to inheriting bias with respect to sensitive attributes such as race and gender, which can lead to life-altering outcomes (e.g., demographic bias in facial recognition software used to arrest a suspect). We propose a robust optimization problem, which we demonstrate can improve fairness in several datasets, both synthetic and real-world, using an affine linear model. Leveraging second order information, we are able to find a solution to our optimization problem more efficiently than a purely first order method.