Training Latent Diffusion Models with Interacting Particle Algorithms
Machine Learning
2026-03-31 v3 Machine Learning
Abstract
We introduce a novel particle-based algorithm for end-to-end training of latent diffusion models. We reformulate the training task as minimizing a free energy functional and obtain a gradient flow that does so. By approximating the latter with a system of interacting particles, we obtain the algorithm, which we underpin theoretically by providing error guarantees. The novel algorithm compares favorably in experiments with previous particle-based methods and variational inference analogues.
Cite
@article{arxiv.2505.12412,
title = {Training Latent Diffusion Models with Interacting Particle Algorithms},
author = {Tim Y. J. Wang and Juan Kuntz and O. Deniz Akyildiz},
journal= {arXiv preprint arXiv:2505.12412},
year = {2026}
}
Comments
Camera Ready version for AISTATS 2026