arXiv：cs.LG· Angshuman Chakravertty, P V V Raj·· 5 小时前AI 评分37
缺失的隐变量而非模拟器缺陷：面向真实 JWST 反演的半径增强推理
A Missing Latent, Not a Missing Simulator: Radius-Augmented Inference for Real JWST Retrieval
AI 导读
针对摊销模拟推理（SBI）在真实 JWST 光谱上失效的问题，研究者提出半径增强的流匹配后验方法 MIRAGE，将真实 WASP-39b 的拟合从 χ²/N=301 降至 0.06。嵌套采样排除了温度梯度、SO2 不透明度和高保真不透明度集等前向模型因素，表明崩溃源于推理遗漏了行星半径这一模拟器已编码的隐变量。该方法无需改动即可迁移至两台仪器和三个真实 JWST 目标。
正文
Abstract:Amortized simulation-based inference (SBI), which is trained on radiative-transfer simulators, recovers exoplanet atmospheres accurately on synthetic James Webb Space Telescope (JWST) spectra but collapses when it comes to real reduced spectra. The flow posterior collapsed on real WASP-39b (importance-sampling effective sample size (ESS) = 1, best-fit \c{hi}2/N = 301), and such a failure is usually blamed on missing the forward-model physics, but ruling these levers out with nested sampling first (a temperature gradient, SO2 opacity, and a high-fidelity opacity set) leaves the fit unchanged, meaning the collapse is not from the simulator misspecification but instead from a missing latent, the planet radius. To fix this, we build MIRAGE, a radius-augmented flow-matching posterior calibrated against an independent nested-sampling reference with importance sampling and an optimal-transport map, which yields a physical and literature-consistent retrieval of real WASP-39b (with \c{hi}2/N from 301 to 0.06). This same method transfers unchanged across two instruments and three real JWST targets, including one spectrum self-reduced end-to-end from raw Mikulski Archive for Space Telescopes(MAST) data. The lesson is cross-domain, as a latent the simulator encodes but the inference omits can masquerade as misspecification.
| Comments: | 6 pages, 2 figures, 2 tables. Includes appendix and paper checklist |
| Subjects: | Instrumentation and Methods for Astrophysics (astro-ph.IM); Earth and Planetary Astrophysics (astro-ph.EP); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.02245 [astro-ph.IM] |
| (or arXiv:2610.02245v1 [astro-ph.IM] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02245 arXiv-issued DOI via DataCite |
Submission history
From: Angshuman Chakravertty [view email]
[v1]
Wed, 30 Sep 2026 08:33:16 UTC (1,930 KB)
来源：arXiv：cs.LG · arxiv.org