Predictive artificial intelligence (AI) systems based on deep learning have been shown to
achieve expert-level identification of diseases in multiple medical imaging settings, but can …

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 …

Learning with abstention is a key scenario where the learner can abstain from making a
prediction at some cost. In this paper, we analyze the score-based formulation of learning …

We study the key framework of learning with abstention in the multi-class classification
setting. In this setting, the learner can choose to abstain from making a prediction with some …

Enabling machine learning classifiers to defer their decision to a downstream expert when
the expert is more accurate will ensure improved safety and performance. This objective can …

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 …

Cascades are a classical strategy to enable inference cost to vary adaptively across
samples, wherein a sequence of classifiers are invoked in turn. A deferral rule determines …

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 …

Since the explosion in popularity of ChatGPT, large language models (LLMs) have
continued to impact our everyday lives. Equipped with external tools that are designed for a …

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 …