Sliding-Window Reordering with Overlap Averaging: A Simple Time-Domain Augmentation for Multivariate Forecasting
Augmentation has become a central technique for improving deep forecasting models, but classification-style transformations tend to break the coherence between the look-back window and its continuous future target. We describe a simple procedure that unfolds the joint input-target sequence into overlapping sliding windows, randomly reorders a controlled fraction of them-prioritized by a lightweight variance criterion-and reconstructs the sequence by averaging across the overlaps, producing synthetic samples with controlled variation while limiting temporal distortion. The procedure is model-agnostic, introduces only three interpretable hyperparameters, and achieves strong improvements ove...
| Authors | Jafar Bakhshaliyev, Johannes Burchert, Niels Landwehr et al. |
|---|---|
| Primary category | cs.LG |
| Published | 10 April 2026 |
| Last updated at source | 3 September 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.