Metraipolis › archive › dc_ff536642b009

Principled Koopman Representations with Kalman Inference for Efficient Time-Series Prediction — arXiv:2609.17815

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.17815
License (as archived)
CC0-1.0
Archived
2026-10-15T15:04:25.990Z
SHA-256 of the archived text
2ad8fb6eb49c15114c674d885fc4fc9bb653a8b505f0dc6be2406fac10c5d015
Stable URL of this page
https://metraipolis.com/documento/dc_ff536642b009

How to cite

Principled Koopman Representations with Kalman Inference for Efficient Time-Series Prediction — arXiv:2609.17815 — arXiv (en), https://arxiv.org/abs/2609.17815 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff536642b009 (Metraipolis archive dc_ff536642b009, sha256 2ad8fb6eb49c15114c674d885fc4fc9bb653a8b505f0dc6be2406fac10c5d015)
BibTeX
@misc{dcff536642b009,
  title = {Principled Koopman Representations with Kalman Inference for Efficient Time-Series Prediction — arXiv:2609.17815},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17815},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff536642b009; sha256 2ad8fb6eb49c15114c674d885fc4fc9bb653a8b505f0dc6be2406fac10c5d015},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17815. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The Koopman operator has been widely used for time-series prediction in dynamical systems. However, prior work that learns latent ``Koopman spaces'' using neural networks often did not construct a valid Koopman space for forecasting, as these representations may be mathematically inconsistent with the operator-theoretic formulation and fail to capture the intrinsic low-rank structure of system dynamics. To address this issue, we introduce K$^2$SVD, a method that explicitly learns the leading singular functions of the Koopman operator by optimizing a Hilbert-Schmidt objective. This yields a well-defined low-rank approximation of the Koopman operator with an interpretable linear combination, featuring a compact latent space with less than $10\%$ of the dimensions used in previous work. In the learned Koopman space, K$^2$SVD further captures temporal evolution with a linear Gaussian state-space model and performs inference via Kalman filtering, mitigating noise accumulation during multi-step prediction. Empirical results show that K$^2$SVD outperforms state-of-the-art methods across multiple datasets, with significantly faster prediction speeds and lower computational cost than previous efficiency-focused models. This highlights the benefits of principled low-rank Koopman representations and opens up broader potential for applications.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.17815 — 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 2026-10-15T14:08:19.068Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).