ICLR 2018poster12891 citations

mixup: Beyond Empirical Risk Minimization

Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, David Lopez-Paz

Abstract

Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple learning principle to alleviate these issues. In essence, mixup trains a neural network on convex combinations of pairs of examples and their labels. By doing so, mixup regularizes the neural network to favor simple linear behavior in-between training examples. Our experiments on the ImageNet-2012, CIFAR-10, CIFAR-100, Google commands and UCI datasets show that mixup improves the generalization of state-of-the-art neural network architectures. We also find that mixup reduces the memorization of corrupt labels, increases the robustness to adversarial examples, and stabilizes the training of generative adversarial networks.

empirical risk minimizationvicinal risk minimizationgeneralizationdata augmentationimage classificationgenerative adversarial networksadversarial examplesrandom labels
BibTeX
@inproceedings{
zhang2018mixup,
title={mixup: Beyond Empirical Risk Minimization},
author={Hongyi Zhang and Moustapha Cisse and Yann N. Dauphin and David Lopez-Paz},
booktitle={International Conference on Learning Representations},
year={2018},
url={https://openreview.net/forum?id=r1Ddp1-Rb},
}
mixup: Beyond Empirical Risk Minimization · ICLR 2018