用粒子算法训练潜在扩散模型，理论可靠且效果更优。
Training Latent Diffusion Models with Interacting Particle Algorithms
- 将训练转为最小化自由能泛函的梯度流
- 粒子系统逼近实现端到端训练，误差可保证
- 比已有粒子法和变分方法更高效可靠
我们提出一种新型基于粒子的算法，用于潜在扩散模型的端到端训练。将训练任务重新表述为最小化自由能泛函，并导出相应的梯度流。通过用相互作用粒子系统近似该梯度流，得到具体算法，并从理论上提供了误差保证。实验表明，该方法在性能上优于先前的粒子基方法及变分推断类方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。