Metraipolis › archive › dc_3dac83d371cb
Spatiotemporal Kronecker Covariance Neural Networks — arXiv:2609.25326
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25326
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T15:07:23.325Z
- SHA-256 of the archived text
d882cabe3ffbc65d434d9d313315fa29fe7e49ec903ac05d653238d9cca90fdf- Stable URL of this page
https://metraipolis.com/documento/dc_3dac83d371cb
How to cite
Spatiotemporal Kronecker Covariance Neural Networks — arXiv:2609.25326 — arXiv (en), https://arxiv.org/abs/2609.25326 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3dac83d371cb (Metraipolis archive dc_3dac83d371cb, sha256 d882cabe3ffbc65d434d9d313315fa29fe7e49ec903ac05d653238d9cca90fdf)
BibTeX
@misc{dc3dac83d371cb,
title = {Spatiotemporal Kronecker Covariance Neural Networks — arXiv:2609.25326},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25326},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3dac83d371cb; sha256 d882cabe3ffbc65d434d9d313315fa29fe7e49ec903ac05d653238d9cca90fdf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25326. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multivariate time series contain complex patterns that span across both space and time. While covariance-based statistical tools like spatiotemporal Principal Component Analysis (ST-PCA) help identify these patterns, they are limited to linear operations and prone to estimation errors with limited data. Recent covariance-based spatiotemporal neural networks offer more stable, non-linear alternatives, but they ignore correlations across different time steps. To solve this, we introduce the Kronecker coVariance Neural Network (KVNN), a temporal graph neural network that represents the spatiotemporal covariance matrix via a sum of Kronecker products where spatial and temporal dependencies are decoupled. By implementing filtering operations on spatial and temporal components, KVNNs achieve expressive processing capabilities, admit a rigorous spectral analysis, and are provably stable to finite-sample estimation errors, ultimately addressing all of ST-PCA's limitations. We show on five real-world datasets that KVNNs achieve strong forecasting performance, often requiring significantly fewer trainable parameters than competitive methods, and are consistent under estimation noise. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.25326 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T14:37:29.385Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).