Neural Posterior Estimation methods for simulation-based inference can be ill-suited for dealing with posterior distributions obtained by conditioning on multiple observations, as they tend to require a large number of simulator calls to learn accurate approximations. In contrast, Neural Likelihood Estimation methods can handle multiple observations at inference time after learning from individual observations, but they rely on standard inference methods, such as MCMC or variational inference, which come with certain performance drawbacks. We introduce a new method based on conditional score modeling that enjoys the benefits of both approaches. We model the scores of the (diffused) posterior distributions induced by individual observations, and introduce a way of combining the learned scores to approximately sample from the target posterior distribution. Our approach is sample-efficient, can naturally aggregate multiple observations at inference time, and avoids the drawbacks of standard inference methods.

翻译：基于模拟推理的神经后验估计方法在处理通过多个观测条件化得到的后验分布时可能不适用，因为它们通常需要大量模拟器调用来学习精确近似。相反，神经似然估计方法可以在从单个观测学习后在推理时处理多个观测，但它们依赖于标准推理方法（如MCMC或变分推理），这些方法存在一定的性能缺陷。我们提出了一种基于条件分数建模的新方法，该方法兼具两种方法的优势。我们对由单个观测诱导的（扩散）后验分布的分数进行建模，并引入一种组合所学分数的方法，以近似从目标后验分布中采样。我们的方法样本高效，能够在推理时自然地聚合多个观测，并避免了标准推理方法的缺陷。