Metraipolis › archive › dc_eb0c6530e5ea

The Information Limits of Neural Controlled Differential Equations Under Sparse Observations — arXiv:2611.03887

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03887
License (as archived)
CC0-1.0
Archived
2026-11-04T21:50:51.072Z
SHA-256 of the archived text
344a8090a48e2400f5a0519c51404f4c95a894d76008351b0a71a1031b6830d5
Stable URL of this page
https://metraipolis.com/documento/dc_eb0c6530e5ea

How to cite

The Information Limits of Neural Controlled Differential Equations Under Sparse Observations — arXiv:2611.03887 — arXiv (en), https://arxiv.org/abs/2611.03887 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb0c6530e5ea (Metraipolis archive dc_eb0c6530e5ea, sha256 344a8090a48e2400f5a0519c51404f4c95a894d76008351b0a71a1031b6830d5)
BibTeX
@misc{dceb0c6530e5ea,
  title = {The Information Limits of Neural Controlled Differential Equations Under Sparse Observations — arXiv:2611.03887},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03887},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb0c6530e5ea; sha256 344a8090a48e2400f5a0519c51404f4c95a894d76008351b0a71a1031b6830d5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03887. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural controlled differential equations (Neural CDEs) evolve hidden states along continuous paths constructed by interpolating discrete observations. Sparse measurements leave the input between observation times undetermined, and admissible continuous paths consistent with the same data can produce different terminal states. We characterize this ambiguity for planar drivers with bounded speed. The set of compatible terminal states admits a leading-order zonotopic approximation determined by feasible signed areas and transported Lie brackets. Its projection onto a scalar prediction yields a computable, target-specific ambiguity certificate. We also study the number of measurements needed to reduce the remaining uncertainty. For nondegenerate planar CDEs, the optimal worst-case radius over deterministic adaptive sampling policies scales as $N^{-1}$ when speed is bounded and $N^{-2}$ when both speed and acceleration are bounded, where $N$ is the number of observation intervals. Synthetic experiments assess the certificate using admissible continuous completions and examine the role of path regularity.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.03887 — 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 2026-11-04T21:38:49.678Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).