Metraipolis › archive › dc_7c442435eb04

Inverse Cross-spectral Neural Networks for Multivariate Time Series — arXiv:2610.06630

Source
arXiv
Original
https://arxiv.org/abs/2610.06630
License (as archived)
CC0-1.0
Archived
2026-10-06T05:32:33.301Z
SHA-256 of the archived text
fb938fa4d553160ae31fb06b74c325af12c73f9bceddf2b0b87fc03951892fca
Stable URL of this page
https://metraipolis.com/documento/dc_7c442435eb04

How to cite

Inverse Cross-spectral Neural Networks for Multivariate Time Series — arXiv:2610.06630 — arXiv, https://arxiv.org/abs/2610.06630 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7c442435eb04 (Metraipolis archive dc_7c442435eb04, sha256 fb938fa4d553160ae31fb06b74c325af12c73f9bceddf2b0b87fc03951892fca)
BibTeX
@misc{dc7c442435eb04,
  title = {Inverse Cross-spectral Neural Networks for Multivariate Time Series — arXiv:2610.06630},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06630},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7c442435eb04; sha256 fb938fa4d553160ae31fb06b74c325af12c73f9bceddf2b0b87fc03951892fca},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06630. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

CoVariance Neural Networks and their extensions have emerged as effective tools for processing multivariate data, deriving graph shift operators directly from second-order statistics. These architectures, however, are designed for independent and identically distributed observations and do not fully capture the joint structure of temporal and cross-variable dependencies in multivariate time series. In this work, we introduce Inverse Cross-Spectral Neural Networks (iCSNNs), a class of graph neural networks for stationary multivariate time series whose shift operators are the inverse cross-spectral density (iCSD) matrices. These operators encode frequency-specific conditional relationships among variables, exploiting the decomposition provided by the spectral representation theorem. Leveraging spectral smoothness, frequencies are grouped into bands sharing a single iCSD operator, yielding a compact parametrisation that retains the frequency-dependent structure of the process. We further propose a joint learning procedure to estimate both the Fourier-domain dependence structure and the iCSNN parameters, adapting the iCSD operators to the downstream task. When tested on synthetic data, iCSNN outperforms baselines from different methodological families.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Signal Processing (eess.SP); Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2610.06630 — 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 2026-10-06T05:27:06.045Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).