Unifying GANs and Score-Based Diffusion as Generative Particle Models

by   Jean-Yves Franceschi, et al.
ETH Zurich

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 by 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.


page 7

page 16

page 25

page 26


MonoFlow: Rethinking Divergence GANs via the Perspective of Differential Equations

The conventional understanding of adversarial training in generative adv...

From Points to Functions: Infinite-dimensional Representations in Diffusion Models

Diffusion-based generative models learn to iteratively transfer unstruct...

SPI-GAN: Distilling Score-based Generative Models with Straight-Path Interpolations

Score-based generative models (SGMs) are a recently proposed paradigm fo...

Latent diffusion models for generative precipitation nowcasting with accurate uncertainty quantification

Diffusion models have been widely adopted in image generation, producing...

Generative Ensemble-Regression: Learning Stochastic Dynamics from Discrete Particle Ensemble Observations

We propose a new method for inferring the governing stochastic ordinary ...

WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points

Generative adversarial networks (GAN) are a widely used class of deep ge...

Please sign up or login with your details

Forgot password? Click here to reset