Reviews: Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer

The paper studies the interaction between an automated model and a decision-maker. The authors refer to this new model of learning as learning-to-defer and provide connections between this model, rejection learning and mixture of experts model of learning. The paper proposes approaches to solve learning-to-defer and experimentally evaluate these approaches on fairness-sensitive datasets. Questions: (1) Is there any particular reason for choosing neural networks as the binary classifier versus other methods? The COMPAS dataset has been studied for fairness-accuracy trade-offs in many other previous works with different learning methods.