Metraipolis › archive › dc_330f52c3bd2f

Exact signal recovery from generative priors with sigmoid output activation — arXiv:2611.05626

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05626
License (as archived)
CC0-1.0
Archived
2026-11-05T18:27:05.569Z
SHA-256 of the archived text
99df1715a1bcd74ec520afc1510603f72f8b797e45feb9132566444be7821482
Stable URL of this page
https://metraipolis.com/documento/dc_330f52c3bd2f

How to cite

Exact signal recovery from generative priors with sigmoid output activation — arXiv:2611.05626 — arXiv (en), https://arxiv.org/abs/2611.05626 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_330f52c3bd2f (Metraipolis archive dc_330f52c3bd2f, sha256 99df1715a1bcd74ec520afc1510603f72f8b797e45feb9132566444be7821482)
BibTeX
@misc{dc330f52c3bd2f,
  title = {Exact signal recovery from generative priors with sigmoid output activation — arXiv:2611.05626},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05626},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_330f52c3bd2f; sha256 99df1715a1bcd74ec520afc1510603f72f8b797e45feb9132566444be7821482},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05626. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We show exact signal recovery in generative compressed sensing for feedforward neural networks with piecewise-linear activations and a final sigmoid activation, with no assumption of expansivity. Consider a ReLU network of depth $d$ with a sigmoid final activation, whose input layer, of dimension $k$, is the narrowest, and let $K$ be the geometric mean of the widths of its layers. We show that, with high probability, all signals of the range whose entries lie in $[\delta, 1 - \delta]$ are uniformly recovered from $m \gtrsim k(d \log(K/k) + \log(1+\log(1/\delta)))$ measurements.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno).
Categorie arXiv: Information Theory (cs.IT) ; Signal Processing (eess.SP); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.05626 — 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 2026-11-05T18:16:33.997Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).