Data Augmentation Policy Search for Long-Term Forecasting

Published: 10 Feb 2025, Last Modified: 10 Feb 2025Accepted by TMLREveryoneRevisionsBibTeXCC BY 4.0
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 a non-augmented model for a limited number of epochs, followed by an iterative split procedure. During this iterative process, we alternate between identifying a robust augmentation policy through Bayesian optimization and refining the model while discarding suboptimal runs. Extensive evaluations on challenging univariate and multivariate forecasting benchmark problems demonstrate that TSAA consistently outperforms several robust baselines, suggesting its potential integration into prediction pipelines. Code is available at this repository: \href{https://github.com/azencot-group/TSAA}{https://github.com/azencot-group/TSAA}.
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: Camera ready
Code: https://github.com/azencot-group/TSAA
Assigned Action Editor: ~Mingsheng_Long2
Submission Number: 2855
Loading