arXiv:2604.09414v3 Announce Type: replace-cross Abstract: A learning-to-defer (L2D) system decides, for each input, whether to predict on its own or to hand it to one of several available experts. The very well established recipe trains classifier and router jointly by treating the $K$ classes and $J$ experts as competing actions in one shared $(K{+}J)$-action geometry. Subsequent work has proposed a series of incremental fixes within this geometry; we show that each still suffers, to varying severity, from an optimization-level pathology (target distortion, gradient amplification, winner-take
Source: arXiv cs.LG — read the full report at the original publisher.