Metraipolis › archive › dc_f7b45284ccfd

Uncertainty propagation in auto-regressive random neural network models — arXiv:2608.20483

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20483
License (as archived)
CC0-1.0
Archived
2026-10-18T10:31:21.524Z
SHA-256 of the archived text
f2f3f6b8086d6f8cb67a05862de2f5996e54af12492372415c07f60f54fa7008
Stable URL of this page
https://metraipolis.com/documento/dc_f7b45284ccfd

How to cite

Uncertainty propagation in auto-regressive random neural network models — arXiv:2608.20483 — arXiv (en), https://arxiv.org/abs/2608.20483 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f7b45284ccfd (Metraipolis archive dc_f7b45284ccfd, sha256 f2f3f6b8086d6f8cb67a05862de2f5996e54af12492372415c07f60f54fa7008)
BibTeX
@misc{dcf7b45284ccfd,
  title = {Uncertainty propagation in auto-regressive random neural network models — arXiv:2608.20483},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20483},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f7b45284ccfd; sha256 f2f3f6b8086d6f8cb67a05862de2f5996e54af12492372415c07f60f54fa7008},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20483. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We develop analytical and particle-based methods for uncertainty propagation in random neural network models, where both the inputs and network parameters are allowed to be random. Building on the piecewise-linear structure of the Leaky ReLU activation function, we derive a local approximation of the neural network output with respect to perturbations in both its inputs and parameters. This approximation is exact for perturbations that preserve the network activation pattern, and it allows us to compute analytical expressions for the probability density function and characteristic function of the network output, together with closed-form approximations for its mean and covariance. We extend this uncertainty propagation framework to autonomous dynamical systems whose one-step evolution map is represented by a random neural network. Repeated application of this map defines an autoregressive model, for which we derive recursive equations to propagate uncertainty in both the state and network parameters over time. These equations explicitly account for the state-parameter cross-covariance that develops under successive iterations of the network. Numerical experiments on the Lorenz-63 system and the Kuramoto-Sivashinsky equation demonstrate accurate uncertainty propagation through the predictability horizon and the applicability of the proposed framework to high-dimensional dynamical systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Computational Physics (physics.comp-ph).
Pagina del lavoro: https://arxiv.org/abs/2608.20483 — 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 2026-10-18T10:27:55.974Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).