Data Augmentation vs. Equivariant Networks: A Theory of Generalization on Dynamics Forecasting

Abstract

Exploiting symmetry in dynamical systems is a powerful way to improve the generalization of deep learning. The model learns to be invariant to transformation, and hence is more robust to distribution shift. Data augmentation and equivariant networks are two major approaches to inject symmetry into learning. However, their exact role in improving generalization is not well understood. In this work, we derive the generalization bounds for data augmentation and equivariant networks, characterizing their effect on learning in a unified framework. Unlike most prior theories for the i.i.d. setting, we focus on non-stationary dynamics forecasting with complex temporal dependencies.