用多精度模拟降低宇宙学推断成本，提升小样本下推断精度。

Simulation-Efficient Cosmological Inference with Multi-Fidelity SBI

• 融合高低精度模拟数据，通过特征匹配与知识蒸馏提升效率
• 在少量模拟预算下显著改善后验分布质量，尤其适合难题
• 适合资源有限但需高精度推断的宇宙学研究者

宇宙学基于模拟的推断所需仿真成本可通过结合不同精度的模拟集来降低。本文提出一种基于特征匹配与知识蒸馏的多精度推断方法。该方法在小规模仿真预算及复杂推断问题中均表现出更优的后验质量，显著提升了计算效率与精度，适用于资源受限但要求高可靠性的宇宙学参数估计场景。

原文摘要 · Abstract (English)

The simulation cost for cosmological simulation-based inference can be decreased by combining simulation sets of varying fidelity. We propose an approach to such multi-fidelity inference based on feature matching and knowledge distillation. Our method results in improved posterior quality, particularly for small simulation budgets and difficult inference problems.

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。