Classification with Deep Neural Networks and Logistic Loss

arXiv:2307.16792v2 Announce Type: replace-cross
Abstract: Deep neural networks (DNNs) trained with the logistic loss (i.e., the cross entropy loss) have made impressive advancements in various binary classification tasks. However, generalization analysis for binary classification with DNNs and logistic loss remains scarce. The unboundedness of the target function for the logistic loss is the main obstacle to deriving satisfactory generalization bounds. In this paper, we aim to fill this gap by establishing a novel and elegant oracle-type inequality, which enables us …

abstract analysis arxiv binary classification cs.lg entropy function however logistic loss networks neural networks stat.ml tasks type