When No-Rejection Learning is Consistent for Regression with Rejection

arXiv:2307.02932v3 Announce Type: replace
Abstract: Learning with rejection has been a prototypical model for studying the human-AI interaction on prediction tasks. Upon the arrival of a sample instance, the model first uses a rejector to decide whether to accept and use the AI predictor to make a prediction or reject and defer the sample to humans. Learning such a model changes the structure of the original loss function and often results in undesirable non-convexity and inconsistency issues. For the classification …

abstract arxiv consistent cs.lg human instance prediction regression sample studying tasks type