Top-$k$ Classification and Cardinality-Aware Prediction

arXiv:2403.19625v1 Announce Type: new
Abstract: We present a detailed study of top-$k$ classification, the task of predicting the $k$ most probable classes for an input, extending beyond single-class prediction. We demonstrate that several prevalent surrogate loss functions in multi-class classification, such as comp-sum and constrained losses, are supported by $H$-consistency bounds with respect to the top-$k$ loss. These bounds guarantee consistency in relation to the hypothesis set $H$, providing stronger guarantees than Bayes-consistency due to their non-asymptotic and hypothesis-set specific …

abstract arxiv beyond class classification cs.lg functions loss losses prediction stat.ml study type