Data Augmentation Policy Search for Long-Term Forecasting

arXiv:2405.00319v1 Announce Type: new
Abstract: Data augmentation serves as a popular regularization technique to combat overfitting challenges in neural networks. While automatic augmentation has demonstrated success in image classification tasks, its application to time-series problems, particularly in long-term forecasting, has received comparatively less attention. To address this gap, we introduce a time-series automatic augmentation approach named TSAA, which is both efficient and easy to implement. The solution involves tackling the associated bilevel optimization problem through a two-step process: initially training …

abstract application arxiv attention augmentation challenges classification combat cs.ai cs.lg data forecasting gap image long-term networks neural networks overfitting policy popular regularization search series success tasks type while