Score: 0

Training Latent Diffusion Models with Interacting Particle Algorithms

Published: May 18, 2025 | arXiv ID: 2505.12412v2

By: Tim Y. J. Wang, Juan Kuntz, O. Deniz Akyildiz

Potential Business Impact:

Makes AI create pictures from just words.

Business Areas:
Peer to Peer Collaboration

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.

Country of Origin
🇬🇧 United Kingdom

Page Count
25 pages

Category
Statistics:
Machine Learning (Stat)