Why Mixup Improves the Model Performance
arXiv:2006.06231
Abstract
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.
References in corpus (7)
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
- Data Augmentation Generative Adversarial Networks
- Random Erasing Data Augmentation
- Manifold Mixup: Better Representations by Interpolating Hidden States
- Data Augmentation by Pairing Samples for Images Classification
- Norm-Based Capacity Control in Neural Networks
- Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup