Data Augmentation Policy Search for Long-Term Forecasting

TMLR Paper2855 Authors

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.

Submission Length: Regular submission (no more than 12 pages of main content)

Changes Since Last Submission: We addressed each of the reviewers' comments. All changes are marked in red. Specifically, we extended our discussion around the mathematical equations, we added new results ablating TSAA vs. DA from scratch, we improved the visualization of Fig. 5, added bar charts of the main results, added extended results for AutoAugment methods, and limitation discussion for the Exchange dataset.

Assigned Action Editor: ~Mingsheng_Long2

Submission Number: 2855