Continuous-Time Functional Diffusion Processes

03/01/2023
by   Giulio Franzese, et al.
0

We introduce functional diffusion processes (FDPs), which generalize traditional score-based diffusion models to infinite-dimensional function spaces. FDPs require a new mathematical framework to describe the forward and backward dynamics, and several extensions to derive practical training objectives. These include infinite-dimensional versions of the Girsanov theorem, in order to be able to compute an ELBO, and of the sampling theorem, in order to guarantee that functional evaluations in a countable set of points are equivalent to infinite-dimensional functions. We use FDPs to build a new breed of generative models in function spaces, which do not require specialized network architectures, and that can work with any kind of continuous data. Our results on synthetic and real data illustrate the advantages of FDPs in simplifying the design requirements of diffusion models.

READ FULL TEXT
research
02/20/2023

Infinite-Dimensional Diffusion Models for Function Spaces

We define diffusion-based generative models in infinite dimensions, and ...
research
12/01/2022

Diffusion Generative Models in Infinite Dimensions

Diffusion generative models have recently been applied to domains where ...
research
05/18/2023

Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces

Typical generative diffusion models rely on a Gaussian diffusion process...
research
09/28/2022

Spectral Diffusion Processes

Score-based generative modelling (SGM) has proven to be a very effective...
research
03/08/2023

Multilevel Diffusion: Infinite Dimensional Score-Based Diffusion Models for Image Generation

Score-based diffusion models (SBDM) have recently emerged as state-of-th...
research
06/06/2018

On Bayesian inferential tasks with infinite-state jump processes: efficient data augmentation

Advances in sampling schemes for Markov jump processes have recently ena...
research
07/11/2023

Geometric Neural Diffusion Processes

Denoising diffusion models have proven to be a flexible and effective pa...

Please sign up or login with your details

Forgot password? Click here to reset