Metraipolis › archive › dc_c2d71c53e02c

PAC-Bayesian Bounds for Learning Partially Observed Stochastic Linear Time-Invariant State-Space Systems with Inputs and Sub-Gaussian Noise — arXiv:2609.08740

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.08740
License (as archived)
CC0-1.0
Archived
2026-10-16T13:58:24.250Z
SHA-256 of the archived text
fe51a020f506e9645fd64f34abe5c71b6b344063bff8f346fadbc99b69cb9838
Stable URL of this page
https://metraipolis.com/documento/dc_c2d71c53e02c

How to cite

PAC-Bayesian Bounds for Learning Partially Observed Stochastic Linear Time-Invariant State-Space Systems with Inputs and Sub-Gaussian Noise — arXiv:2609.08740 — arXiv (en), https://arxiv.org/abs/2609.08740 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c2d71c53e02c (Metraipolis archive dc_c2d71c53e02c, sha256 fe51a020f506e9645fd64f34abe5c71b6b344063bff8f346fadbc99b69cb9838)
BibTeX
@misc{dcc2d71c53e02c,
  title = {PAC-Bayesian Bounds for Learning Partially Observed Stochastic Linear Time-Invariant State-Space Systems with Inputs and Sub-Gaussian Noise — arXiv:2609.08740},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.08740},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c2d71c53e02c; sha256 fe51a020f506e9645fd64f34abe5c71b6b344063bff8f346fadbc99b69cb9838},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08740. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this paper we derive a Probably Approximately Correct (PAC)-Bayesian error bound for partially observed linear time-invariant (LTI) stochastic dynamical systems in state-space form with inputs and sub-Gaussian noise. Such bounds are widespread in machine learning, and they are useful for characterizing the predictive power of models learned from finitely many data points. The bound derived in this paper relates the expectation of prediction errors with the prediction error generated by the model on the data used for learning. In addition, we show that it can also be used to derive bounds for the parameter estimation error. In turn, this allows us to provide finite-sample error bounds for the prediction error and parameter estimation error for a wide class of system identification algorithms. Furthermore, as LTI systems are a sub-class of recurrent neural networks (RNNs), these error bounds could be a first step towards PAC-Bayesian bounds for RNNs.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.08740 — 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 2026-10-16T13:39:43.067Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).