Metraipolis › archive › dc_72c677387bb2

Target-Dependent Limits of Causal Repair: A Leading-Log Frontier in a Gaussian Model — arXiv:2610.00424

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00424
License (as archived)
CC0-1.0
Archived
2026-10-06T12:09:29.961Z
SHA-256 of the archived text
ab57c2d6974d54c13518160edbfa32735d0027b5ce59027042e0c263417aebb0
Stable URL of this page
https://metraipolis.com/documento/dc_72c677387bb2

How to cite

Target-Dependent Limits of Causal Repair: A Leading-Log Frontier in a Gaussian Model — arXiv:2610.00424 — arXiv (en), https://arxiv.org/abs/2610.00424 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_72c677387bb2 (Metraipolis archive dc_72c677387bb2, sha256 ab57c2d6974d54c13518160edbfa32735d0027b5ce59027042e0c263417aebb0)
BibTeX
@misc{dc72c677387bb2,
  title = {Target-Dependent Limits of Causal Repair: A Leading-Log Frontier in a Gaussian Model — arXiv:2610.00424},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00424},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_72c677387bb2; sha256 ab57c2d6974d54c13518160edbfa32735d0027b5ce59027042e0c263417aebb0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00424. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Knowing how much a causal predictor could improve need not reveal the gain of the repair actually learned. We quantify this gap in a scalar Gaussian causal experiment with known intervention geometry: auxiliary data identify effect magnitude up to bounded contamination, while diagnostics identify direction. The target is the squared-loss gain of the realized trained repair relative to a fitted reference. Jointly optimizing the learner and assessor under uniform learning MSE $\eta$ avoids the trivial solution of making no repair. At the usual $1/k$ learning scale, every feasible learner incurs a $k^{-2}$ assessment floor, even when oracle potential is estimable at a faster rate. In the magnitude-rich regime, we characterize a sharp leading-log frontier: the assessment exponent is $\min{\ell_k,2k\eta_k/U}$ to first relative order, where $\ell_k=\log(1/(k^2E_k))$ and $E_k$ is auxiliary precision. A diagnostic-abstention rule attains this exponent with unknown nuisance parameters. We also bound the critical allowance window and transfer the frontier to adaptive sampling by exact Gaussian simulation. Finite-grid experiments distinguish sign-tail suppression from total MSE and expose conservative finite-budget behavior. The result isolates how the assessment target changes information requirements in this experiment; it is not a general causal identifiability claim.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Machine Learning (stat.ML) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.00424 — 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 2026-10-06T10:21:28.068Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).