Learning fair predictors with Sensitive Subspace Robustness

As artificial intelligence (AI) systems permeate our world, the problem of implicit biases in these systems have become more serious. AI systems are routinely used to make decisions or support the decision-making process in credit, hiring, criminal justice, and education, all of which are domains protected by anti-discrimination law. Although AI systems appear to eliminate the biases of a human decision maker, they may perpetuate or even exacerbate biases in the training data [64]. Such biases are especially objectionable when it adversely affects underprivileged groups of users [3]. Although the most obvious remedy is to remove the biases in the training data, this is impractical in most applications.