高维潜在空间中的基于模拟的推断
High-Dimensional Simulation-Based Inference in Latent Spaces
浏览论文内容
中文总结 AI 辅助
本文提出将模拟推断与潜在生成建模结合，在低维潜在空间中进行后验推断并映射回原参数空间，在匹配计算下达到同等精度且采样快一个数量级以上。
中文摘要 AI 辅助
神经模拟推断（SBI）在从可能高维的观测数据（如图像或时间序列）中推断相对较少的可解释参数方面取得了广泛成功。因此，SBI中的表示学习几乎完全集中在压缩用于条件后验的观测数据上。然而，最近SBI开始针对日益高维的参数空间，提出了一个互补的问题：推断目标本身是否也应该被压缩。我们的答案是将SBI与潜在生成建模实用地结合起来，学习模拟器参数的低维表示，直接在此潜在空间中进行后验推断，并将后验样本映射回原始参数空间。我们刻画了潜在空间推断恢复所需目标后验的条件，并系统研究了其经验权衡。在四个案例研究和三个生成家族中，我们在控制网络容量、正则化、优化和训练计算的同时，比较了潜在估计器和标准估计器。在匹配的训练计算下，潜在空间推断实现了与直接目标空间推断相当的准确性和边际校准，同时采样速度提升了一个数量级以上。
英文摘要
Neural simulation-based inference (SBI) has been widely successful in inferring a relatively small number of interpretable parameters from potentially high-dimensional observations, such as images or time series. Accordingly, representation learning in SBI has focused almost exclusively on compressing the observations used to condition the posterior. More recently, however, SBI has begun to target increasingly high-dimensional parameter spaces, raising the complementary question of whether the inference target itself should be compressed. Our answer is a practical merger of SBI and latent generative modeling, which learns a low-dimensional representation of the simulator parameters, performs posterior inference directly in this latent space, and maps posterior samples back to the original parameter space. We characterize the conditions under which latent-space inference recovers the desired target posterior and systematically study its empirical trade-offs. Across four case studies and three generative families, we compare latent and standard estimators while controlling for network capacity, regularization, optimization, and training compute. At matched training compute, latent-space inference achieves accuracy and marginal calibration comparable to direct target-space inference while sampling up to more than an order of magnitude faster.
发表机构
- TU Dortmund University（多特蒙德工业大学）
- Rensselaer Polytechnic Institute（伦斯勒理工学院）
机构由 AI 辅助整理，请以论文原文为准。
