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.

翻译：我们提出了一种新颖的基于粒子的端到端训练潜扩散模型的算法。我们将训练任务重新表述为最小化自由能泛函，并推导出实现该目标的梯度流。通过用交互粒子系统近似该梯度流，我们得到了所提出的算法，并为其提供了理论上的误差保证。实验表明，该新算法相较于先前的基于粒子的方法和变分推理类比方法具有更优的性能。