# Negative Log Likelihood Ratio Loss for Deep Neural Network Classification

Source: [Negative Log Likelihood Ratio Loss for Deep Neural Network Classification](<https://www.sota2.com/research/paper/68fa644e1e209131cea03e7a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:35.846Z

Authors: Donglai Zhu, Hengshuai Yao, Bei Jiang, Peng Yu

Published: 2018-04-27T21:24:59.000Z

## Abstract

In deep neural network, the cross-entropy loss function is commonly used for classification. Minimizing cross-entropy is equivalent to maximizing likelihood under assumptions of uniform feature and class distributions. It belongs to generative training criteria which does not directly discriminate correct class from competing classes. We propose a discriminative loss function with negative log likelihood ratio between correct and competing classes. It significantly outperforms the cross-entropy loss on the CIFAR-10 image classification task.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1804.10690>)

[PDF](<https://arxiv.org/pdf/1804.10690.pdf>)