Metraipolis › archive › dc_58375388692a
Tensor Network Moral Graph Recovery of Discrete Probability Distributions — arXiv:2609.09258
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.09258
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:51:44.912Z
- SHA-256 of the archived text
71b0322d6b93e38ae27441f16dfa1d9ab2e9944d8b116562975a325327c6d9ba- Stable URL of this page
https://metraipolis.com/documento/dc_58375388692a
How to cite
Tensor Network Moral Graph Recovery of Discrete Probability Distributions — arXiv:2609.09258 — arXiv (en), https://arxiv.org/abs/2609.09258 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_58375388692a (Metraipolis archive dc_58375388692a, sha256 71b0322d6b93e38ae27441f16dfa1d9ab2e9944d8b116562975a325327c6d9ba)
BibTeX
@misc{dc58375388692a,
title = {Tensor Network Moral Graph Recovery of Discrete Probability Distributions — arXiv:2609.09258},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.09258},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_58375388692a; sha256 71b0322d6b93e38ae27441f16dfa1d9ab2e9944d8b116562975a325327c6d9ba},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09258. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present a method for recovering the moral graph of a causal DAG from a probability distribution over discrete variables, using fully connected tensor networks (FCTNs) with nuclear-norm-regularized bond corrections. Each bond matrix is parameterized as a baseline all-ones matrix plus a low-rank correction $C_{ij} = U_{ij}V_{ij}^\top$, and the nuclear norm of the correction implemented via the variational Frobenius norm penalty on the factors drives unnecessary bonds to zero. We prove that under faithfulness, positivity, and a no-implicit-rerouting assumption on the local tensor architecture, \textbf{every} optimal FCTN with zero reconstruction error $\varepsilon = 0$ has effective graph exactly equal to the moral graph. For the approximate regime ($\varepsilon > 0$), we provide explicit recovery bounds using the Fannes-Audenaert continuity of conditional mutual information, and derive a sufficient condition on the regularization parameter $\beta$. The effective graph is read directly from the optimized bond matrices.
Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-10 in math.PR).
Categorie arXiv: Machine Learning (stat.ML) ; Information Theory (cs.IT); Machine Learning (cs.LG); Probability (math.PR); Quantum Physics (quant-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.09258 — 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 2026-10-16T08:44:35.305Z dalla pagina https://arxiv.org/catchup/math.PR/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).