Metraipolis › archive › dc_3aef63d36f25

The Statistical Cost of Causal Discovery with Feedback — arXiv:2609.34050

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34050
License (as archived)
CC0-1.0
Archived
2026-10-07T22:40:18.375Z
SHA-256 of the archived text
babbe6aae957c5ee5da22d61b024904745604fb8b42ce54c424f93fc9d1b1776
Stable URL of this page
https://metraipolis.com/documento/dc_3aef63d36f25

How to cite

The Statistical Cost of Causal Discovery with Feedback — arXiv:2609.34050 — arXiv (en), https://arxiv.org/abs/2609.34050 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3aef63d36f25 (Metraipolis archive dc_3aef63d36f25, sha256 babbe6aae957c5ee5da22d61b024904745604fb8b42ce54c424f93fc9d1b1776)
BibTeX
@misc{dc3aef63d36f25,
  title = {The Statistical Cost of Causal Discovery with Feedback — arXiv:2609.34050},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34050},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3aef63d36f25; sha256 babbe6aae957c5ee5da22d61b024904745604fb8b42ce54c424f93fc9d1b1776},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34050. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

What determines the unavoidable sample cost of learning cyclic causal structure? For cyclic linear non-Gaussian models, we study exact condensation recovery from observational data: identifying the strongly connected component (SCC) partition and all edges between components. We establish the first information-theoretic lower bounds on sample complexity for this target. For $p$ variables, maximum SCC size $s_{\max}$, and maximum external-parent count $d_B$, any estimator requires order $s_{\max}\log(ep/s_{\max})+d_B\log(ep/d_B)$ samples in the worst case over a regular model class. These bounds distinguish the costs of SCC membership and external-parent selection. Under principal invertibility and without correlation faithfulness, we establish a population block-exogeneity principle that identifies unknown root SCCs through residual independence and inclusion minimality. A sparse-adjustment characterization shows that small adjustment sets suffice to identify SCCs and their direct external parents, without regressing on all previously recovered variables. These characterizations yield BlockExo, which attains a structurally matching sample bound without knowing $s_{\max}$ or $d_B$ under suitable conditions. Simulations support the structural dependence of our sample bound and demonstrate BlockExo's sample-efficient recovery in comparisons with other methods for cyclic causal discovery.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.34050 — 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 2026-10-07T22:14:28.811Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).