Metraipolis › archive › dc_3ce17ec9341d

Correct then Forecast: Observer State-Space Models for Time Series Forecasting — arXiv:2609.33566

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33566
License (as archived)
CC0-1.0
Archived
2026-10-07T22:37:34.856Z
SHA-256 of the archived text
65b3dd57e4f8e3180be9f81fdeda0fbf7052b64e7671fe7936012bb949b29459
Stable URL of this page
https://metraipolis.com/documento/dc_3ce17ec9341d

How to cite

Correct then Forecast: Observer State-Space Models for Time Series Forecasting — arXiv:2609.33566 — arXiv (en), https://arxiv.org/abs/2609.33566 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ce17ec9341d (Metraipolis archive dc_3ce17ec9341d, sha256 65b3dd57e4f8e3180be9f81fdeda0fbf7052b64e7671fe7936012bb949b29459)
BibTeX
@misc{dc3ce17ec9341d,
  title = {Correct then Forecast: Observer State-Space Models for Time Series Forecasting — arXiv:2609.33566},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33566},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ce17ec9341d; sha256 65b3dd57e4f8e3180be9f81fdeda0fbf7052b64e7671fe7936012bb949b29459},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33566. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Time series forecasting requires extrapolating the dynamics of an observed process beyond the last available measurement. Yet recurrent forecasting models typically treat observations as inputs that directly control their latent dynamics. It leads to a regime change when these observations become unavailable at prediction time. Following a state-estimation perspective, we introduce Observer State-Space Models (OSSMs), a class of recurrent models that interprets the observed input time series as measurements of an underlying autonomous dynamical system. OSSMs explicitly separate latent-state propagation from measurement assimilation: a single transition governs the dynamics across both context and forecasting intervals, while available observations correct the estimated state through an observer. This formulation naturally exposes classical control-theoretic properties, including observability and convergence of the state estimation error. We further show that conventional and recent SSMs can be recovered as particular instances of our OSSM framework, thereby providing a unified interpretation of their recurrent dynamics and revealing modeling inconsistencies. We perform experiments across several benchmarks showing that OSSM achieves substantial improvements while maintaining the same parameter count and training setup as the corresponding SSM baseline. These results support a simple principle for recurrent forecasting: observations should correct the estimated latent state, rather than control the dynamics used to propagate it.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.33566 — 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 2026-10-07T22:14:27.986Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).