Metraipolis › archive › dc_af143fe1fb13

PAC-Bayesian Meta-Learning for Few-Shot Identification of Linear Dynamical Systems — arXiv:2609.24117

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24117
License (as archived)
CC0-1.0
Archived
2026-10-09T07:07:33.136Z
SHA-256 of the archived text
2c6a925122a76bf9f95b5e0a5ce969b8c2a10ff37973cd4864cae28d9d7ef4bf
Stable URL of this page
https://metraipolis.com/documento/dc_af143fe1fb13

How to cite

PAC-Bayesian Meta-Learning for Few-Shot Identification of Linear Dynamical Systems — arXiv:2609.24117 — arXiv (en), https://arxiv.org/abs/2609.24117 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af143fe1fb13 (Metraipolis archive dc_af143fe1fb13, sha256 2c6a925122a76bf9f95b5e0a5ce969b8c2a10ff37973cd4864cae28d9d7ef4bf)
BibTeX
@misc{dcaf143fe1fb13,
  title = {PAC-Bayesian Meta-Learning for Few-Shot Identification of Linear Dynamical Systems — arXiv:2609.24117},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24117},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af143fe1fb13; sha256 2c6a925122a76bf9f95b5e0a5ce969b8c2a10ff37973cd4864cae28d9d7ef4bf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24117. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Identifying linear time-invariant (LTI) dynamical systems is challenging when trajectories are short, noisy, or high-dimensional. Traditional system identification typically treats each system independently and cannot exploit shared structure across related systems. We propose PBML-LTI, a PAC-Bayesian meta-learning framework for few-shot LTI system identification that learns a transferable prior over task-specific dynamics while preserving task heterogeneity. Each task corresponds to an unknown LTI system, and the meta-learner uses training trajectories to learn a data-dependent prior over transition matrices. For a new system with limited data, PBML-LTI performs Bayesian adaptation under this prior to obtain a task-specific posterior, providing accurate estimates and principled uncertainty quantification. A key challenge is temporal dependence, since LTI trajectories violate the i.i.d. assumptions underlying most PAC-Bayes meta-learning analyses. We address this with a martingale PAC-Bayes analysis for dependent trajectory losses and derive a support-query predictive-risk bound that motivates a fit-KL meta-training objective. The bound clarifies the roles of empirical fit, posterior complexity, and prior quality in few-shot adaptation under sequential dependence. We further derive corollaries for transition-matrix recovery and multi-step trajectory prediction, connecting uncertainty-aware meta-identification with finite-sample guarantees for dependent dynamical data.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.24117 — 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 2026-10-09T06:58:09.371Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).