Metraipolis › archive › dc_f395ff4e2457

Training-Free Bottleneck Width Planning for Convolutional Autoencoders — arXiv:2609.30755

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30755
License (as archived)
CC0-1.0
Archived
2026-10-08T03:12:33.126Z
SHA-256 of the archived text
0185f9b851fb857e3abcb3cd50af4c76d2370a917580441688b60e25dc15b5e2
Stable URL of this page
https://metraipolis.com/documento/dc_f395ff4e2457

How to cite

Training-Free Bottleneck Width Planning for Convolutional Autoencoders — arXiv:2609.30755 — arXiv (en), https://arxiv.org/abs/2609.30755 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f395ff4e2457 (Metraipolis archive dc_f395ff4e2457, sha256 0185f9b851fb857e3abcb3cd50af4c76d2370a917580441688b60e25dc15b5e2)
BibTeX
@misc{dcf395ff4e2457,
  title = {Training-Free Bottleneck Width Planning for Convolutional Autoencoders — arXiv:2609.30755},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30755},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f395ff4e2457; sha256 0185f9b851fb857e3abcb3cd50af4c76d2370a917580441688b60e25dc15b5e2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30755. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multiscale Spectral Rate-Distortion (MS-SRD) estimates the bottleneck channels required at user-supplied spatial cuts from training images and a normalized mean-squared error (NMSE) bound, without fitting a neural network. Its covariance-tail rule is exact for shared linear block-convolutional autoencoders under squared error. A nested-scale dominance result motivates reporting the activation-parameter Pareto frontier alongside the minimum-latent candidate. At NMSE <= 0.01 on thirteen grayscale datasets, its latent-size prediction has 0.84% mean absolute percentage error against nonlinear patch-autoencoder boundaries; ten predictions are exact and the remaining three differ by one channel. In a four-dataset deployable comparison, MS-SRD matches all retrospective external widths and all four selected models pass, without training a selector; a 46-fit validation grid and four Least-Volume fits each pass on two datasets. In a skip-closed U-shaped autoencoder at the same bound, five predictions are exact, nine are within one channel, and every failing prediction is one channel short. Experiments at looser bounds show progressively larger nonlinear savings.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.30755 — 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 2026-10-08T02:50:19.045Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).