Metraipolis › archive › dc_1522ec77c835

FOCUS: Fixed-Confidence Online Causal Learning Using Sequential Adaptive Interventions — arXiv:2609.32165

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32165
License (as archived)
CC0-1.0
Archived
2026-10-07T22:39:34.212Z
SHA-256 of the archived text
fb7347cb3ffa9459ddbd8f79db33b0951413467d0459bf253942d6b06df13d0a
Stable URL of this page
https://metraipolis.com/documento/dc_1522ec77c835

How to cite

FOCUS: Fixed-Confidence Online Causal Learning Using Sequential Adaptive Interventions — arXiv:2609.32165 — arXiv (en), https://arxiv.org/abs/2609.32165 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1522ec77c835 (Metraipolis archive dc_1522ec77c835, sha256 fb7347cb3ffa9459ddbd8f79db33b0951413467d0459bf253942d6b06df13d0a)
BibTeX
@misc{dc1522ec77c835,
  title = {FOCUS: Fixed-Confidence Online Causal Learning Using Sequential Adaptive Interventions — arXiv:2609.32165},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32165},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1522ec77c835; sha256 fb7347cb3ffa9459ddbd8f79db33b0951413467d0459bf253942d6b06df13d0a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32165. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study fully online fixed-confidence causal discovery without any historical observational data. Starting from zero samples, the learner sequentially selects interventions to recover both the causal DAG and its edge weights under a linear-Gaussian structural equation model. We establish an instance-dependent lower bound for any $(\epsilon,\delta)$-correct algorithm and propose \textsc{FOCUS}, which adaptively allocates interventions through an online max--min game. A key contribution is a computable concentration inequality for the accumulated KL divergence involving causal parameters shared across interventions. We prove that \textsc{FOCUS} is $(\epsilon,\delta)$-correct and that its expected stopping time matches the lower bound in its $\Theta(\log(1/\delta))$ dependence up to an instance-dependent constant. Experiments demonstrate improved structure and edge-weight recovery and confirm the predicted stopping-time trend. Our codes are available on this https URL

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/2609.32165 — 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 2026-10-07T22:14:28.576Z 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).