Discrimination in Algorithmic Decision Making: From Principles to Measures and Mechanisms

The rise of algorithmic decision making in a variety of applications has also raised concerns about its potential for discrimination against certain social groups. However, incorporating nondiscrimination goals into the design of algorithmic decision making systems (or, classifiers) has proven to be quite challenging. These challenges arise mainly due to the computational complexities involved in the process, and the inadequacy of existing measures to computationally capture discrimination in various situations. The goal of this thesis is to tackle these problems. First, with the aim of incorporating existing measures of discrimination (namely, disparate treatment and disparate impact) into the design of well-known classifiers, we introduce a mechanism of decision boundary covariance, that can be included in the formulation of any convex boundary-based classifier in the form of convex constraints. Second, we propose alternative measures of discrimination. Our first proposed measure, disparate mistreatment, is useful in situations when unbiased ground truth training data is available. The other two measures, preferred treatment and preferred impact, are useful in situations when feature and class distributions of different social groups are significantly different, and can additionally help reduce the cost of nondiscrimination (as compared to the existing measures). We also design mechanisms to incorporate these new measures into the design of convex boundary-based classifiers