On some theoretical limitations of Generative Adversarial Networks - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

On some theoretical limitations of Generative Adversarial Networks

Résumé

Generative Adversarial Networks have become a core technique in Machine Learning to generate unknown distributions from data samples. They have been used in a wide range of context without paying much attention to the possible theoretical limitations of those models. Indeed, because of the universal approximation properties of Neural Networks, it is a general assumption that GANs can generate any probability distribution. Recently, people began to question this assumption and this article is in line with this thinking. We provide a new result based on Extreme Value Theory showing that GANs can't generate heavy tailed distributions. The full proof of this result is given.
Fichier principal
Vignette du fichier
2110.10915.pdf (124.16 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04069825 , version 1 (31-05-2024)

Identifiants

Citer

Benoit Oriol, Alexandre Miot. On some theoretical limitations of Generative Adversarial Networks. 2021. ⟨hal-04069825⟩
13 Consultations
15 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More