不要偷工减料：如何在先验之外训练让基于模拟的推理更鲁棒
Don't Cut Corners: How Training Outside the Prior Makes Simulation-Based Inference More Robust
AI总结：
针对天体物理模拟训练数据的先验边界问题，提出Tailed-Uniform混合提议分布，经其训练的神经后验估计器在高维场景下，于先验边界附近及之外的后验估计准确性显著提升。
AI中文摘要：
大型天体物理模拟项目通常通过在均匀先验框内采样参数生成训练数据。由于该提议的尖锐边界，神经后验估计器难以学习边界附近的准确近似。我们提出Tailed-Uniform，这是一种用于采样训练模拟以实现鲁棒基于模拟推理的混合提议分布族。通过用衰减尾部填充原始硬截断训练框，经Tailed-Uniform训练的网络在边界附近及之外能产生更准确的后验。我们在包括作为对照的加宽均匀框在内的一系列尾部形状上展示了这些改进。结果表明，即使对于假设的均匀先验，先验边界附近的额外模拟也能更好地约束接近训练框边缘的网络。我们在一个玩具问题和基于物质功率谱的宇宙学参数推理上展示了这些优势，且这些优势在高维空间中会增强，因为边界主导了参数空间体积。
英文摘要：
Large astrophysical simulation campaigns often generate training data by sampling parameters across a Uniform prior box. Due to the proposal's sharp edge, neural posterior estimators struggle to learn accurate approximations near the boundaries. We propose Tailed-Uniform, a family of hybrid proposal distributions for sampling training simulations for robust simulation-based inference. By padding the original hard-truncated training box with decaying tails, Tailed-Uniform-trained networks yield more accurate posteriors near and beyond the edges. We demonstrate these improvements on a family of tail shapes, including a widened Uniform box as a control. Our results suggest that additional simulations near the prior boundary better constrain the networks as it approaches the edge of the training box, even for Uniform assumed priors. We show these advantages on a toy problem and cosmological parameter inference from the matter power spectrum. These benefits increase in high dimensions, where boundaries dominate parameter space volume.
