AI advice is becoming increasingly popular, eg, in investment and medical treatment
decisions. As this advice is typically imperfect, decision-makers have to exert discretion as to …

We study a two-stage scenario for learning to defer with multiple experts, which is crucial in
practice for many applications. In this scenario, a predictor is derived in a first stage by …

Recent work has proposed artificial intelligence (AI) models that can learn to decide whether
to make a prediction for an instance of a task or to delegate it to a human by considering …

We present a comprehensive study of surrogate loss functions for learning to defer. We
introduce a broad family of surrogate losses, parameterized by a non-increasing function …

The learning to defer (L2D) framework allows autonomous systems to be safe and robust by
allocating difficult decisions to a human expert. All existing work on L2D assumes that each …

Artificial intelligence (AI) can improve human decision-making in various application areas.
Ideally, collaboration between humans and AI should lead to complementary team …

We present a study of surrogate losses and algorithms for the general problem of learning to
defer with multiple experts. We first introduce a new family of surrogate losses specifically …

We study the statistical properties of learning to defer (L2D) to multiple experts. In particular,
we address the open problems of deriving a consistent surrogate loss, confidence …

Learning to defer with multiple experts is a framework where the learner can choose to defer
the prediction to several experts. While this problem has received significant attention in …

The surging global demand for mental healthcare (MH) services has amplified the interest in
utilizing AI-assisted technologies in critical MH components, including assessment and …