NeurIPS 2025poster0 citations
A solvable model of learning generative diffusion: theory and insights
Hugo Cui, Cengiz Pehlevan, Yue M. Lu
Abstract
In this manuscript, we analyze a solvable model of flow or diffusion-based generative model. We consider the problem of learning a model parametrized by a two-layer auto-encoder, trained with online stochastic gradient descent, on a high-dimensional target density with an underlying low-dimensional manifold structure. We derive a tight asymptotic characterization of low-dimensional projections of the distribution of samples generated by the learned model, ascertaining in particular its dependence on the number of training samples. Building on this analysis, we discuss how mode collapse can arise, and lead to model collapse when the generative model is re-trained on generated synthetic data.
high-dimensional asymptoticsstatistical physicsdiffusion model
BibTeX
@inproceedings{
cui2025a,
title={A solvable model of learning generative diffusion: theory and insights},
author={Hugo Cui and Cengiz Pehlevan and Yue M. Lu},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=5b5wZg6Zeo}
}