Communication Dans Un Congrès Année : 2025

On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity

Résumé

Modern deep generative models can now produce high-quality synthetic samples that are often indistinguishable from real training data. A growing body of research aims to understand why recent methods -such as diffusion and flow matching techniques -generalize so effectively. Among the proposed explanations are the inductive biases of deep learning architectures and the stochastic nature of the conditional flow matching loss. In this work, we rule out the latter -the noisy nature of the loss -as a primary contributor to generalization in flow matching. First, we empirically show that in high-dimensional settings, the stochastic and closed-form versions of the flow matching loss yield nearly equivalent losses. Then, using state-of-the-art flow matching models on standard image datasets, we demonstrate that both variants achieve comparable statistical performance, with the surprising observation that using the closed-form can even improve performance. * Equal contribution.

Fichier principal
Vignette du fichier
2506.03719v1.pdf (2.53 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05119547 , version 1 (18-06-2025)

Licence

Identifiants

  • HAL Id : hal-05119547 , version 1

Citer

Quentin Bertrand, Anne Gagneux, Mathurin Massias, Rémi Emonet. On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity. NeurIPS 2025 - 39th Annual Conference on Neural Information Processing Systems, Dec 2025, San Diego (CA), United States. ⟨hal-05119547⟩
1078 Consultations
412 Téléchargements

Partager

  • More