Metraipolis › archive › dc_f4f9fc2919de
Spectral characteristics of autoencoder parameters as a vector representation of data — arXiv:2609.03495
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03495
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T02:07:56.006Z
- SHA-256 of the archived text
a0f68fbcfdb119175630a647cb876f9f6b630d0e8fd24513b0a5a549580332f0- Stable URL of this page
https://metraipolis.com/documento/dc_f4f9fc2919de
How to cite
Spectral characteristics of autoencoder parameters as a vector representation of data — arXiv:2609.03495 — arXiv (en), https://arxiv.org/abs/2609.03495 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f4f9fc2919de (Metraipolis archive dc_f4f9fc2919de, sha256 a0f68fbcfdb119175630a647cb876f9f6b630d0e8fd24513b0a5a549580332f0)
BibTeX
@misc{dcf4f9fc2919de,
title = {Spectral characteristics of autoencoder parameters as a vector representation of data — arXiv:2609.03495},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03495},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f4f9fc2919de; sha256 a0f68fbcfdb119175630a647cb876f9f6b630d0e8fd24513b0a5a549580332f0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03495. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper examines the relationship between the parameters of autoencoder models and the statistical properties of the data on which they are trained. Autoencoders are defined as models with an encoder-decoder architecture, trained to reconstruct input data through a compressed latent representation. It is proposed that the model parameters can be viewed as a dense vector representation of the corresponding sample. To test this hypothesis, a theoretical and experimental study is conducted in which a vector representation is formed based on the spectral characteristics of the autoencoder parameter matrices. Theoretical analysis shows that the singular values of the model parameter matrices are related to the eigenvalues of the covariance matrix of the training data, ensuring the transfer of information between the data space and the parameter space. Experimental results on the CIFAR-10 and FashionMNIST datasets confirm that the resulting vector representations allow for a high degree of accuracy in distinguishing between models trained on different data subsets, without resorting to complex vector generation algorithms or using the original samples. These results suggest that the parameters of trained autoencoders can be viewed as sample representations. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.03495 — 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 2026-10-17T01:47:25.552Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).