Metraipolis › archive › dc_ab8a19ac586c

Local Fisher Information Enables Sparse Causal Discovery — arXiv:2610.04291

Source
arXiv
Original
https://arxiv.org/abs/2610.04291
License (as archived)
CC0-1.0
Archived
2026-10-06T05:32:03.822Z
SHA-256 of the archived text
2b5d80455659da83e74f2b0324927dcba3dafb6b69b2b60028b45483b1d7fcea
Stable URL of this page
https://metraipolis.com/documento/dc_ab8a19ac586c

How to cite

Local Fisher Information Enables Sparse Causal Discovery — arXiv:2610.04291 — arXiv, https://arxiv.org/abs/2610.04291 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ab8a19ac586c (Metraipolis archive dc_ab8a19ac586c, sha256 2b5d80455659da83e74f2b0324927dcba3dafb6b69b2b60028b45483b1d7fcea)
BibTeX
@misc{dcab8a19ac586c,
  title = {Local Fisher Information Enables Sparse Causal Discovery — arXiv:2610.04291},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04291},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ab8a19ac586c; sha256 2b5d80455659da83e74f2b0324927dcba3dafb6b69b2b60028b45483b1d7fcea},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04291. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sparse causal discovery calls for methods that exploit graph structure without estimating high-dimensional densities. We introduce Fisher Information Completion Search (FiCS), a source-first algorithm for additive noise models that uses one local Fisher score for both ordering and parent selection. Under regularity and nonconstant-parent conditions, we prove that a node's local Fisher information equals the noise Fisher information exactly when the conditioning set contains all parents, provided that it contains no descendants. This Fisher parent completion identifies the parent set as the unique minimal Fisher completion. With a maximum conditioning set size $q$ at least the maximum indegree $d$, population FiCS queries marginals of at most $q+1$ variables and recovers the true directed acyclic graph under a positive ordering margin. Bounded conditioning also has a population advantage: reducing $q$ toward $d$ cannot decrease, and can strictly increase, the ordering margin. A growing non-Gaussian family separates local Fisher selection from conditional-variance and leaf-first Fisher ordering. For the regularized kernel Stein estimator, we establish high-dimensional DAG consistency under $q\{1+\log(p/q)\}+\log p=o(n)$, uniform Fisher separation, local approximation, and compatible ridge and parent penalty parameters. Experiments show the strongest gains when $n$ is small relative to $p$, quantify the effect of the conditioning size, and demonstrate competitive reference-graph recovery on three real-data benchmarks.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.04291 — 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 2026-10-06T05:27:05.955Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).