Wavelet Score-Based Generative Modeling

08/09/2022
by   Florentin Guth, et al.
9

Score-based generative models (SGMs) synthesize new data samples from Gaussian white noise by running a time-reversed Stochastic Differential Equation (SDE) whose drift coefficient depends on some probabilistic score. The discretization of such SDEs typically requires a large number of time steps and hence a high computational cost. This is because of ill-conditioning properties of the score that we analyze mathematically. We show that SGMs can be considerably accelerated, by factorizing the data distribution into a product of conditional probabilities of wavelet coefficients across scales. The resulting Wavelet Score-based Generative Model (WSGM) synthesizes wavelet coefficients with the same number of time steps at all scales, and its time complexity therefore grows linearly with the image size. This is proved mathematically over Gaussian distributions, and shown numerically over physical processes at phase transition and natural image datasets.

READ FULL TEXT

page 3

page 9

page 39

research
07/09/2021

Wavelet Transform-assisted Adaptive Generative Modeling for Colorization

Unsupervised deep learning has recently demonstrated the promise to prod...
research
09/29/2022

Denoising MCMC for Accelerating Diffusion-Based Generative Models

Diffusion models are powerful generative models that simulate the revers...
research
06/13/2022

Convergence for score-based generative modeling with polynomial complexity

Score-based generative modeling (SGM) is a highly successful approach fo...
research
06/01/2021

Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling

Progressively applying Gaussian noise transforms complex data distributi...
research
03/21/2023

Universal Smoothed Score Functions for Generative Modeling

We consider the problem of generative modeling based on smoothing an unk...
research
07/11/2022

Wavelet Conditional Renormalization Group

We develop a multiscale approach to estimate high-dimensional probabilit...
research
03/23/2021

Out-of-Distribution Detection of Melanoma using Normalizing Flows

Generative modelling has been a topic at the forefront of machine learni...

Please sign up or login with your details

Forgot password? Click here to reset