Training Latent Diffusion Models with Interacting Particle Algorithms
This work addresses training challenges in latent diffusion models for machine learning applications, representing an incremental improvement.
The authors tackled the problem of training latent diffusion models by introducing a particle-based algorithm that minimizes a free energy functional, achieving favorable experimental results compared to previous methods.
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.