arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2006.06231stat.MLcs.LG
收藏

为什么Mixup可以提高模型性能

Why Mixup Improves the Model Performance

Ridge-i Inc.(Ridge-i公司)

Masanari Kimura

摘要:

机器学习技术在广泛的领域中使用。然而,机器学习模型经常遭受过拟合的问题。已经提出了许多数据增强方法来解决这样的问题,其中之一被称为mixup。Mixup是最近提出的正则化过程,它线性插值一对随机的训练样本。这种正则化方法在实验上工作得很好,但其理论保证没有得到充分的讨论。本研究从统计学习理论的角度探讨了混淆学习的有效性。

英文摘要:

Machine learning techniques are used in a wide range of domains. However, machine learning models often suffer from the problem of over-fitting. Many data augmentation methods have been proposed to tackle such a problem, and one of them is called mixup. Mixup is a recently proposed regularization procedure, which linearly interpolates a random pair of training examples. This regularization method works very well experimentally, but its theoretical guarantee is not adequately discussed. In this study, we aim to discover why mixup works well from the aspect of the statistical learning theory.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑