提出无需解微分方程的扩散模型密度估计新方法。
Diffusion Density Estimators
- 用蒙特卡洛路径积分替代求解概率流微分方程。
- 在标准数据集上实现与传统方法相当的密度估计精度。
- 适合需要高效密度评估的生成模型研究者使用。
本文研究将扩散模型用于神经密度估计的可行性。现有方法通过将生成过程转换为平滑流（概率流ODE），利用黑箱求解器计算给定样本的对数密度。本文提出一种全新方法，无需求解流方程即可计算对数密度，其核心是通过蒙特卡洛方式估计路径积分，该策略与扩散模型的无模拟训练机制一致。同时，论文系统分析了不同训练参数对密度计算精度的影响，为提升模型可扩展性和效率提供了实践洞见。
原文摘要 · Abstract (English)
We investigate the use of diffusion models as neural density estimators. The current approach to this problem involves converting the generative process to a smooth flow, known as the Probability Flow ODE. The log density at a given sample can be obtained by solving the ODE with a black-box solver. We introduce a new, highly parallelizable method that computes log densities without the need to solve a flow. Our approach is based on estimating a path integral by Monte Carlo, in a manner identical to the simulation-free training of diffusion models. We also study how different training parameters affect the accuracy of the density calculation, and offer insights into how these models can be made more scalable and efficient.
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。