Skip to yearly menu bar Skip to main content


Two-Stage Learning to Defer with Multiple Experts

Anqi Mao · Christopher Mohri · Mehryar Mohri · Yutao Zhong

Great Hall & Hall B1+B2 (level 1) #1721
[ ]
Wed 13 Dec 8:45 a.m. PST — 10:45 a.m. PST

Abstract: 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 training with a common loss function such as cross-entropy. In the second stage, a deferral function is learned to assign the most suitable expert to each input. We design a new family of surrogate loss functions for this scenario both in the score-based and the predictor-rejector settings and prove that they are supported by $H$-consistency bounds, which implies their Bayes-consistency. Moreover, we show that, for a constant cost function, our two-stage surrogate losses are realizable $H$-consistent. While the main focus of this work is a theoretical analysis, we also report the results of several experiments on CIFAR-10 and SVHN datasets.

Chat is not available.