Unifying GANs and Score-Based Diffusion as Generative Particle Models - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Unifying GANs and Score-Based Diffusion as Generative Particle Models

Mike Gartrell
  • Fonction : Auteur
Ludovic Dos Santos
Emmanuel de Bézenac
  • Fonction : Auteur
  • PersonId : 1101543
  • IdRef : 259426148
Mickaël Chen
  • Fonction : Auteur
  • PersonId : 1101545
Alain Rakotomamonjy
  • Fonction : Auteur
  • PersonId : 1102415

Résumé

Particle-based deep generative models, such as gradient flows and score-based diffusion models, have recently gained traction thanks to their striking performance. Their principle of displacing particle distributions using differential equations is conventionally seen as opposed to the previously widespread generative adversarial networks (GANs), which involve training a pushforward generator network. In this paper we challenge this interpretation, and propose a novel framework that unifies particle and adversarial generative models by framing generator training as a generalization of particle models. This suggests that a generator is an optional addition to any such generative model. Consequently, integrating a generator into a score-based diffusion model and training a GAN without a generator naturally emerge from our framework. We empirically test the viability of these original models as proofs of concepts of potential applications of our framework.
Fichier principal
Vignette du fichier
gpm.pdf (2.51 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Licence : CC BY - Paternité

Dates et versions

hal-04107806 , version 1 (26-05-2023)
hal-04107806 , version 2 (26-10-2023)
hal-04107806 , version 3 (21-12-2023)

Licence

Paternité

Identifiants

Citer

Jean-Yves Franceschi, Mike Gartrell, Ludovic Dos Santos, Thibaut Issenhuth, Emmanuel de Bézenac, et al.. Unifying GANs and Score-Based Diffusion as Generative Particle Models. Thirty-seventh Conference on Neural Information Processing Systems, Neural Information Processing Systems Foundation, Dec 2023, New Orleans, LA, United States. ⟨hal-04107806v3⟩

Relations

70 Consultations
438 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More