Metraipolis › archive › dc_e42aba5b0efe
Channel-Dependent State Space Model for Multivariate Time Series Forecasting — arXiv:2609.36453
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36453
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:25:50.810Z
- SHA-256 of the archived text
e91b90e3232014472a69b81d39004e96a806c71e866d0567c02a81c29dafd273- Stable URL of this page
https://metraipolis.com/documento/dc_e42aba5b0efe
How to cite
Channel-Dependent State Space Model for Multivariate Time Series Forecasting — arXiv:2609.36453 — arXiv (en), https://arxiv.org/abs/2609.36453 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e42aba5b0efe (Metraipolis archive dc_e42aba5b0efe, sha256 e91b90e3232014472a69b81d39004e96a806c71e866d0567c02a81c29dafd273)
BibTeX
@misc{dce42aba5b0efe,
title = {Channel-Dependent State Space Model for Multivariate Time Series Forecasting — arXiv:2609.36453},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36453},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e42aba5b0efe; sha256 e91b90e3232014472a69b81d39004e96a806c71e866d0567c02a81c29dafd273},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36453. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multivariate time series forecasting (MTSF) is critical across many real-world domains. Existing deep learning approaches fall into two paradigms with distinct limitations: channel-independent (CI) methods unconditionally ignore cross-variable dependencies and model only temporal dynamics, while channel-dependent (CD) methods consider both but typically rely on architectural compromises to mitigate overfitting and computational overhead. We therefore propose Chameleon, a specialized CD state space model (SSM) that enables data-dependent, fine-grained interactions across variables while scaling linearly with their number. By connecting selective SSMs with the Kalman filter, we leverage the missing measurement update in the former for cross-variable modeling while preserving the SSM backbone for robust temporal modeling. We further identify favorable inductive biases of GatedDeltaNet for time series, adapt it as our backbone, and improve generalization through additional techniques, including a previously unexplored stochastic perturbation of reversible instance normalization. On strongly dependent ODE and PEMS datasets, Chameleon achieves the best MSE and MAE across all settings, while its CI ablation and prior CD methods incur 61-178% higher MSE on average. Across 28 standard benchmark settings, Chameleon also achieves better MSE and MAE than each baseline in at least 27 and 22 cases, respectively. Training-time and peak-memory analyses on Traffic and ETT further demonstrate competitive efficiency and favorable memory scalability across different variable counts. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.36453 — 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 2026-10-07T15:54:53.839Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).