ICML 2022spotlight76 citations
When and How Mixup Improves Calibration
Linjun Zhang, Zhun Deng, Kenji Kawaguchi, James Zou
Abstract
In many machine learning applications, it is important for the model to provide confidence scores that accurately capture its prediction uncertainty. Although modern learning methods have achieved great success in predictive accuracy, generating calibrated confidence scores remains a major challenge. Mixup, a popular yet simple data augmentation technique based on taking convex combinations of pairs of training examples, has been empirically found to significantly improve confidence calibration across diverse applications. However, when and how Mixup helps calibration is still a mystery. In this paper, we theoretically prove that Mixup improves calibration in
BibTeX
@InProceedings{pmlr-v162-zhang22f,
title = {When and How Mixup Improves Calibration},
author = {Zhang, Linjun and Deng, Zhun and Kawaguchi, Kenji and Zou, James},
booktitle = {Proceedings of the 39th International Conference on Machine Learning},
pages = {26135--26160},
year = {2022},
editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
volume = {162},
series = {Proceedings of Machine Learning Research},
month = {17--23 Jul},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v162/zhang22f/zhang22f.pdf},
url = {https://proceedings.mlr.press/v162/zhang22f.html},
abstract = {In many machine learning applications, it is important for the model to provide confidence scores that accurately capture its prediction uncertainty. Although modern learning methods have achieved great success in predictive accuracy, generating calibrated confidence scores remains a major challenge. Mixup, a popular yet simple data augmentation technique based on taking convex combinations of pairs of training examples, has been empirically found to significantly improve confidence calibration across diverse applications. However, when and how Mixup helps calibration is still a mystery. In this paper, we theoretically prove that Mixup improves calibration in