Metraipolis › archive › dc_16ff99f7beba

Sigmoid Tensor Decomposition for Compact Representations of Binary Data — arXiv:2611.08020

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08020
License (as archived)
CC0-1.0
Archived
2026-11-06T14:52:30.681Z
SHA-256 of the archived text
e52da27d375d1de3c17269e330708ed39a3b290bf267f8487718af3f9ea7bada
Stable URL of this page
https://metraipolis.com/documento/dc_16ff99f7beba

How to cite

Sigmoid Tensor Decomposition for Compact Representations of Binary Data — arXiv:2611.08020 — arXiv (en), https://arxiv.org/abs/2611.08020 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_16ff99f7beba (Metraipolis archive dc_16ff99f7beba, sha256 e52da27d375d1de3c17269e330708ed39a3b290bf267f8487718af3f9ea7bada)
BibTeX
@misc{dc16ff99f7beba,
  title = {Sigmoid Tensor Decomposition for Compact Representations of Binary Data — arXiv:2611.08020},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08020},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_16ff99f7beba; sha256 e52da27d375d1de3c17269e330708ed39a3b290bf267f8487718af3f9ea7bada},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08020. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Nonlinear low-rank decompositions are receiving growing attention as a way to represent structured data with fewer parameters than conventional linear methods. Existing nonlinear approaches have focused mainly on matrices, which limits their ability to capture multidimensional structure. We propose a nonlinear tensor decomposition based on sigmoid nonlinearization in the Tucker and tensor-train formats. A binary tensor is represented by a low-rank real-valued score tensor, whose parameters are estimated by minimizing the binary cross-entropy loss. The resulting optimization problem is jointly nonconvex, but becomes convex with respect to one factor or score block when the remaining factors are fixed, as in the corresponding matrix case. We evaluate the method on several structured binary tensors and compare it with conventional Tucker and tensor-train decompositions across a range of common ranks. These results indicate that sigmoid nonlinearization is particularly effective in the low-rank regime, where it can provide more accurate binary reconstructions than conventional linear tensor decompositions at comparable model sizes.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.NA, nuovi lavori del giorno).
Categorie arXiv: Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2611.08020 — 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 2026-11-06T14:24:12.608Z dalla pagina https://arxiv.org/list/math.NA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).