Metraipolis › archive › dc_d1b41ed2ca0e

Hessian Rank Constraint for Learning Structure of Nonlinear Latent Variable Models — arXiv:2609.24241

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24241
License (as archived)
CC0-1.0
Archived
2026-10-09T07:07:36.833Z
SHA-256 of the archived text
f54c00ef9d016f5ec3ba4fac31d6fc5e55364400be2b0959711d60e49d7a47b3
Stable URL of this page
https://metraipolis.com/documento/dc_d1b41ed2ca0e

How to cite

Hessian Rank Constraint for Learning Structure of Nonlinear Latent Variable Models — arXiv:2609.24241 — arXiv (en), https://arxiv.org/abs/2609.24241 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d1b41ed2ca0e (Metraipolis archive dc_d1b41ed2ca0e, sha256 f54c00ef9d016f5ec3ba4fac31d6fc5e55364400be2b0959711d60e49d7a47b3)
BibTeX
@misc{dcd1b41ed2ca0e,
  title = {Hessian Rank Constraint for Learning Structure of Nonlinear Latent Variable Models — arXiv:2609.24241},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24241},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d1b41ed2ca0e; sha256 f54c00ef9d016f5ec3ba4fac31d6fc5e55364400be2b0959711d60e49d7a47b3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24241. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Uncovering latent variables and their causal relations from observed data is a fundamental yet challenging problem. Existing methods often rely on restrictive assumptions, such as linear relations or invertible mixing functions. To better address this problem under general nonlinear mixing procedures, we propose a condition called the cross-Hessian Rank Constraint (HRC), which serves as a primitive rank-based tool for nonlinear latent causal discovery. In particular, we show that a rank-based property arises from the cross-Hessian of the observed-data log-density in the nonlinear case, revealing information about the latent variables, and reduces to the Tetrad constraints in the linear Gaussian case. More specifically, when two groups of observed variables are d-separated by a set of lower-dimensional latent variables, the rank of this cross-Hessian is equal to the dimension of the latent variables, under a mild affine derivative assumption on the conditional log-density derivatives. This assumption can be naturally satisfied when the noise level is low or the relevant nonlinearity is moderate. As a downstream application, we instantiate HRC in the pure one-factor measurement setting for locating latent variables and recovering their causal structure up to Markov equivalence. Experimental results on synthetic and real-world datasets support the theoretical claims.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.24241 — 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 2026-10-09T06:58:09.384Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).