Global Well-posedness and Convergence Analysis of Score-based Generative Models via Sharp Lipschitz Estimates

Zur Umkehrbarkeit der statistischen Naturgesetze (Engl.: On the reversibility of the statistical laws of nature)

A. Kolmogorov · 1937

Earlier work this paper cites.

Reverse-time diffusion equation models

B. Anderson · 1982

Earlier work this paper cites.

Convex viscosity solutions and state constraints

O. Alvarez, J.-M. Lasry, and P.-L. Lions · 1997

Earlier work this paper cites.

A global geometric framework for nonlinear dimensionality reduction

J. Tenenbaum, V. Silva, and J. Langford · 2000

Earlier work this paper cites.

Semiconcavity estimates for viscous Hamilton–Jacobi equations

T. Strömberg · 2010

Earlier work this paper cites.

Stochastic differential equations and diffusion processes

N. Ikeda and S. Watanabe · 2014

Earlier work this paper cites.

Deep Learning

I. Goodfellow, Y. Bengio, and A. Courville · 2016

Earlier work this paper cites.

Generative modeling by estimating gradients of the data distribution

Y. Song and S. Ermon · 2019

Earlier work this paper cites.

Diffusion models beat GANs on image synthesis

P. Dhariwal and A. Nichol · 2021

Cited alongside, same era.

Universal approximation for log-concave distributions using well-conditioned normalizing flows

Original

H. Lee, C. Pabbaraju, A. Sevekari, and A. Risteski · 2021

Cited alongside, same era.

Score-based generative modeling through stochastic differential equations

Y. Song, J. Sohl-Dickstein, D. Kingma, A. Kumar, S. Ermon, and B. Poole · 2021

Cited alongside, same era.

Convergence of denoising diffusion models under the manifold hypothesis

V. De Bortoli · 2022

Cited alongside, same era.

Cascaded diffusion models for high fidelity image generation

J. Ho, C. Saharia, W. Chan, D. Fleet, M. Norouzi, and T. Salimans · 2022

Cited alongside, same era.

Soft truncation: A universal training technique of score-based diffusion model for high precision score estimation

Fast sampling of diffusion models with exponential integrator

Original

Q. Zhang and Y. Chen · 2022

Later among the works it cites.

Verifying the union of manifolds hypothesis for image data

B. Brown, A. Caterini, B. Ross, J. Cresswell, and G. Loaiza-Ganem · 2023

Later among the works it cites.

Improved analysis of score-based generative modeling: User-friendly bounds under minimal smoothness assumptions

H. Chen, H. Lee, and J. Lu · 2023

Later among the works it cites.

Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions

Original

S. Chen, S. Chewi, J. Li, Y. Li, A. Salim, and A. Zhang · 2023

Later among the works it cites.

Masked diffusion transformer is a strong image synthesizer

S. Gao, P. Zhou, M-M. Cheng, and S. Yan · 2023

Later among the works it cites.