A Group-Theoretic Framework for Data Augmentation

Abstract

Data augmentation is a widely used trick when training deep neural networks: in addition to the original data, properly transformed data are also added to the training set. However, to the best of our knowledge, a clear mathematical framework to explain the performance benefits of data augmentation is not available. In this paper, we develop such a theoretical framework. We show data augmentation is equivalent to an averaging operation over the orbits of a certain group that keeps the data distribution approximately invariant. We prove that it leads to variance reduction. We study empirical risk minimization, and the examples of exponential families, linear regression, and certain two-layer neural networks. We also discuss how data augmentation could be used in problems with symmetry where other approaches are prevalent, such as in cryo-electron microscopy (cryo-EM).

arXiv commentTo appear in Journal of Machine Learning Research

Cited by in corpus (5)

• Data augmentation instead of explicit regularization
• Implicit Rugosity Regularization via Data Augmentation
• Understanding the Generalization Benefit of Model Invariance from a Data Perspective
• Learning Augmentation Distributions using Transformed Risk Minimization
• Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?