用扩散模型加速复杂系统参数推断，无需似然函数。
ConDiSim: Conditional Diffusion Models for Simulation Based Inference
- 以条件扩散模型模拟数据生成过程，反向去噪估计后验分布。
- 在10个基准问题和2个真实场景中实现高精度后验逼近。
- 适合需要快速推断的仿真推断任务，训练稳定且效率高。
我们提出一种条件扩散模型 ConDiSim，用于具有不可计算似然的复杂系统仿真推断。ConDiSim 利用去噪扩散概率模型近似后验分布，包含添加高斯噪声的前向过程和基于观测数据条件的反向去噪过程。该方法有效捕捉后验分布中的复杂依赖关系与多模态特性。ConDiSim 在十个基准问题和两个真实世界测试问题上进行了评估，表现出优异的后验近似精度，同时保持了训练的计算效率与稳定性。ConDiSim 为仿真推断提供了一个鲁棒且可扩展的框架，尤其适用于需要快速推断的参数推断流程。
原文摘要 · Abstract (English)
We present a conditional diffusion model - ConDiSim, for simulation-based inference of complex systems with intractable likelihoods. ConDiSim leverages denoising diffusion probabilistic models to approximate posterior distributions, consisting of a forward process that adds Gaussian noise to parameters, and a reverse process learning to denoise, conditioned on observed data. This approach effectively captures complex dependencies and multi-modalities within posteriors. ConDiSim is evaluated across ten benchmark problems and two real-world test problems, where it demonstrates effective posterior approximation accuracy while maintaining computational efficiency and stability in model training. ConDiSim offers a robust and extensible framework for simulation-based inference, particularly suitable for parameter inference workflows requiring fast inference methods.
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。