Selective Classification Via Neural Network Training Dynamics. (arXiv:2205.13532v1 [cs.LG])

Selective classification is the task of rejecting inputs a model would
predict incorrectly on through a trade-off between input space coverage and
model accuracy. Current methods for selective classification impose constraints
on either the model architecture or the loss function; this inhibits their
usage in practice. In contrast to prior work, we show that state-of-the-art
selective classification performance can be attained solely from studying the
(discretized) training dynamics of a model. We propose a general framework
that, for a given …

arxiv classification dynamics network network training neural network training