Metraipolis › archive › dc_579282a640bd

How Many Samples Are Needed to Determine Causal Direction? Sharp Minimax Bounds for Bivariate LiNGAM — arXiv:2608.15840

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15840
License (as archived)
CC0-1.0
Archived
2026-10-18T19:44:15.076Z
SHA-256 of the archived text
69f19e2582a8d03ce6a04b5b07fe14cd494bdc24e436fbed518a3d683082d2da
Stable URL of this page
https://metraipolis.com/documento/dc_579282a640bd

How to cite

How Many Samples Are Needed to Determine Causal Direction? Sharp Minimax Bounds for Bivariate LiNGAM — arXiv:2608.15840 — arXiv (en), https://arxiv.org/abs/2608.15840 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_579282a640bd (Metraipolis archive dc_579282a640bd, sha256 69f19e2582a8d03ce6a04b5b07fe14cd494bdc24e436fbed518a3d683082d2da)
BibTeX
@misc{dc579282a640bd,
  title = {How Many Samples Are Needed to Determine Causal Direction? Sharp Minimax Bounds for Bivariate LiNGAM — arXiv:2608.15840},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15840},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_579282a640bd; sha256 69f19e2582a8d03ce6a04b5b07fe14cd494bdc24e436fbed518a3d683082d2da},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15840. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study how many observations are needed to determine the causal direction between two linearly related variables. Classical LiNGAM theory shows that independent non-Gaussian disturbances identify the direction, but does not quantify the difficulty when the causal effect is weak or the disturbances are nearly Gaussian. Let $\beta$ bound the absolute structural coefficient from below, let $\nu$ measure each standardized disturbance's distance from Gaussianity, and let the disturbance scales lie in $[\underline\sigma,\overline\sigma]$. We prove the sharp local minimax law \[ N_2^\star(\beta,\nu,\delta) \asymp \frac{\log(1/\delta)} {d_\beta^2+\beta^2\nu^2}, \qquad d_\beta= \left[\beta^2- \left(1-\frac{\underline\sigma^2}{\overline\sigma^2}\right)\right]_+. \] Previous theory established population identifiability or assumed a fixed separation between the two directions. By contrast, we establish the sharp sample complexity as a joint function of edge strength, distance from Gaussianity, and scale uncertainty, and characterize when identification comes from non-Gaussian dependence or from covariance alone. The proof was independently generated with GPT-5.6 Sol in Codex's Ultra mode during a two-hour session. The human author supplied the prompt and was responsible only forchecking the proof and revising and polishing the manuscript.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG).
Categorie arXiv: Statistics Theory (math.ST) ; Machine Learning (cs.LG); Econometrics (econ.EM); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.15840 — 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 2026-10-18T19:02:44.282Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).