Metraipolis › archive › dc_f8f3d119bf7f

Identifiability of Nonnegative Tensor Decompositions via Positive Scattering — arXiv:2609.11606

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11606
License (as archived)
CC0-1.0
Archived
2026-10-16T05:55:21.141Z
SHA-256 of the archived text
04b1f5ed8ac2195397666afa699a0e9e5e927e94d68f48a1a861f0d8456e49b4
Stable URL of this page
https://metraipolis.com/documento/dc_f8f3d119bf7f

How to cite

Identifiability of Nonnegative Tensor Decompositions via Positive Scattering — arXiv:2609.11606 — arXiv (en), https://arxiv.org/abs/2609.11606 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f8f3d119bf7f (Metraipolis archive dc_f8f3d119bf7f, sha256 04b1f5ed8ac2195397666afa699a0e9e5e927e94d68f48a1a861f0d8456e49b4)
BibTeX
@misc{dcf8f3d119bf7f,
  title = {Identifiability of Nonnegative Tensor Decompositions via Positive Scattering — arXiv:2609.11606},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11606},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f8f3d119bf7f; sha256 04b1f5ed8ac2195397666afa699a0e9e5e927e94d68f48a1a861f0d8456e49b4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11606. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Identifiability of tensor decompositions is often established through linear-algebraic conditions on the factor families. For nonnegative decompositions, however, positivity provides additional information that is not captured by dimension and independence alone: nonnegative terms cannot cancel, and their supports constrain competing decompositions. We introduce a positive scattering term that quantifies this additional source of identifiability and combine it with the dimension budget underlying the Lovitz--Petrov generalization of Kruskal's theorem. For every subset of components, we obtain two sufficient conditions: a threshold of $2|S|-2$ guarantees minimality and nonnegative rank, while the stronger threshold $2|S|-1$ guarantees uniqueness among nonnegative decompositions of the same length. The key result is a positive splitting inequality for irreducible exchanges of nonnegative rank-one tensors, which combines the dimension constraint with support-induced geometric rigidity. Although the scattering term is defined through an optimization over intermediate factor spaces, we show that its mode costs are exactly $0$, $1$, or $+\infty$, yielding an exact activation characterization in terms of graph connectivity. The resulting criterion can strictly certify sparse nonnegative tensor decompositions beyond the reach of Kruskal and Lovitz--Petrov conditions, including examples for which those conditions fail even after reshaping. In the matrix case, the two criteria reduce respectively to full-rank factorization and two-sided separability.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Combinatorics (math.CO); Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2609.11606 — 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 2026-10-16T05:44:25.093Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).