Metraipolis › archive › dc_f04643472baa

Generative Adversarial Network Performance in Low-Dimensional Settings — Europe PMC PMID:39015624

Source
Europe PMC (en)
Original
https://europepmc.org/article/MED/39015624
DOI
10.6028/jres.126.008
License (as archived)
CC0-1.0
Archived
2026-11-04T23:59:55.476Z
SHA-256 of the archived text
bf054f89f5c701421ec9faf01af7f371c724f58d8e4a095d896507b219a32176
Stable URL of this page
https://metraipolis.com/documento/dc_f04643472baa

How to cite

Generative Adversarial Network Performance in Low-Dimensional Settings — Europe PMC PMID:39015624 — Europe PMC (en), https://europepmc.org/article/MED/39015624 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f04643472baa (Metraipolis archive dc_f04643472baa, sha256 bf054f89f5c701421ec9faf01af7f371c724f58d8e4a095d896507b219a32176)
BibTeX
@misc{dcf04643472baa,
  title = {Generative Adversarial Network Performance in Low-Dimensional Settings — Europe PMC PMID:39015624},
  howpublished = {Europe PMC (en)},
  url = {https://europepmc.org/article/MED/39015624},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f04643472baa; sha256 bf054f89f5c701421ec9faf01af7f371c724f58d8e4a095d896507b219a32176},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: Europe PMC (en), https://europepmc.org/article/MED/39015624. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A generative adversarial network (GAN) is an artifcial neural network with a distinctive training architecture, designed to create examples that faithfully reproduce a target distribution. GANs have recently had particular success in applications involving high-dimensional distributions in areas such as image processing. Little work has been reported for low dimensions, where properties of GANs may be better identifed and understood. We studied GAN performance in simulated low-dimensional settings, allowing us to transparently assess effects of target distribution complexity and training data sample size on GAN performance in a simple experiment. This experiment revealed two important forms of GAN error, tail underflling and bridge bias, where the latter is analogous to the tunneling observed in high-dimensional GANs.

Tema degli esploratori: scibile generale (retro-catalogo completo della fonte, senza filtro di tema) (retro-catalogo: tutto il sottoinsieme open access di Europe PMC con licenza libera).
Pubblicazione: Journal of research of the National Institute of Standards and Technology, 2021 (prima pubblicazione 2021-04-20).
Identificativi: PMID 39015624 · PMCID PMC10913853 · DOI 10.6028/jres.126.008.
Parole chiave degli autori: Earth Mover Distance; Generative Adversarial Network; Modeling Error; Mode Tunneling; Target Distribution Complexity; Experiment Protocol.
Pagina: https://europepmc.org/article/MED/39015624 — https://doi.org/10.6028/jres.126.008. Autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza dell'articolo dichiarata da Europe PMC: CC0 (la versione è indicata dall'editore sulla pagina). Abstract riportato senza modifiche al contenuto, con attribuzione; deposito marcato CC0.
Letto il 2026-11-04T23:56:29.589Z tramite l'API REST ufficiale di Europe PMC (EMBL-EBI), nel rispetto del robots.txt e del crawl-delay.