Anchor Data Augmentation

Nora Schneider, Shirin Goshtasbpour, Fernando Perez-Cruz

Keywords: Data Augmentation, Regression, Deep Learning

TL;DR: We present a new data augmentation algorithm inspired from the causality and distributional robustness literature to aid model generalization in regression problems. We demonstrate its efficacy on multiple synthetic and real world datasets.

Abstract: We propose a novel algorithm for data augmentation in nonlinear over-parametrized regression. Our data augmentation algorithm borrows from the literature on causality. Contrary to the current state-of-the-art solutions that rely on modifications of Mixup algorithm, we extend the recently proposed distributionally robust Anchor regression (AR) method for data augmentation. Our Anchor Data Augmentation (ADA) uses several replicas of the modified samples in AR to provide more training examples, leading to more robust regression predictions. We apply ADA to linear and nonlinear regression problems using neural networks. ADA is competitive with state-of-the-art C-Mixup solutions.

Submission Number: 4852