Unveiling the Latent Space Geometry of Push-Forward Generative Models - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Unveiling the Latent Space Geometry of Push-Forward Generative Models

Résumé

Many deep generative models are defined as a push-forward of a Gaussian measure by a continuous generator, such as Generative Adversarial Networks (GANs) or Variational Auto-Encoders (VAEs). This work explores the latent space of such deep generative models. A key issue with these models is their tendency to output samples outside of the support of the target distribution when learning disconnected distributions. We investigate the relationship between the performance of these models and the geometry of their latent space. Building on recent developments in geometric measure theory, we prove a sufficient condition for optimality in the case where the dimension of the latent space is larger than the number of modes. Through experiments on GANs, we demonstrate the validity of our theoretical results and gain new insights into the latent space geometry of these models. Additionally, we propose a truncation method that enforces a simplicial cluster structure in the latent space and improves the performance of GANs.
Fichier principal
Vignette du fichier
issenhuth23a.pdf (4.75 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04401282 , version 1 (17-01-2024)

Identifiants

  • HAL Id : hal-04401282 , version 1

Citer

Issenhuth Thibaut, Tanielian Ugo, Mary Jérémie, Picard David. Unveiling the Latent Space Geometry of Push-Forward Generative Models. International Conference on Machine Learning, Jul 2023, Honolulu (Hawaii), USA, United States. ⟨hal-04401282⟩
41 Consultations
10 Téléchargements

Partager

Gmail Facebook X LinkedIn More