用粒子方法高效学习能量模型，提升生成质量与速度。
Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamics
- 通过粒子系统构建连续时间的随机微分方程求解能量模型。
- 在合成与图像数据上验证，计算效率显著优于传统方法。
- 理论保证收敛性，适合需高效采样的生成建模任务。
我们提出一种基于粒子的算法，用于学习具有能量基础先验的隐变量模型。借助近期在粒子方法求解最大边际似然估计（MMLE）问题上的进展，我们建立了一个连续时间框架，通过定义可证明解决MMLE问题的随机微分方程（SDEs）。将这些SDEs离散化后得到实用算法，并提供该算法收敛性的理论保证。最终在合成数据和图像数据集上进行了实验验证，结果表明基于粒子的方法在计算效率方面有显著提升。
原文摘要 · Abstract (English)
We develop interacting particle algorithms for learning latent variable models with energy-based priors. To do so, we leverage recent developments in particle-based methods for solving maximum marginal likelihood estimation (MMLE) problems. Specifically, we provide a continuous-time framework for learning latent energy-based models, by defining stochastic differential equations (SDEs) that provably solve the MMLE problem. We obtain a practical algorithm as a discretisation of these SDEs and provide theoretical guarantees for the convergence of the proposed algorithm. Finally, we empirically validate the effectiveness of our method on synthetic and image datasets and demonstrate that using a particle based approach offers significant improvement in computational efficiency.
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。