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 \textit{high-dimensional} settings by investigating natural statistical models. Interestingly, the calibration benefit of Mixup increases as the model capacity increases. We support our theories with experiments on common architectures and datasets. In addition, we study how Mixup improves calibration in semi-supervised learning. While incorporating unlabeled data can sometimes make the model less calibrated, adding Mixup training mitigates this issue and provably improves calibration. Our analysis provides new insights and a framework to understand Mixup and calibration.
翻译:在许多机器学习应用中,模型必须提供准确测量预测不确定性的自信分数。 尽管现代学习方法在预测准确性方面取得了巨大成功,但获得校准信心分数仍是一项重大挑战。 混合是一种流行而简单的数据增强技术,其基础是采用各种培训范例的组合组合组合,在经验上发现这种技术可以大大改善不同应用中的信任度校准。 然而,当混ixup帮助校准时和如何帮助校准仍然是个谜。 在本文中,我们理论上证明混ixup通过调查自然统计模型改进了 mixup 环境的校准。 有趣的是,混合的校准效益随着模型能力的增长而增加。 我们用共同结构和数据集的实验来支持我们的理论。 此外,我们研究混成如何改进半监视学习中的校准。 在纳入无标签数据的同时,有时会降低模型的校准,加上混成培训会减轻这一问题,并可以改进校准。 我们的分析提供了新的洞察和校准框架。