Detecting Model Misspecification in Cosmology with Scale-Dependent Normalizing Flows
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911097681870848 |
|---|---|
| author | Akhmetzhanova, Aizhan Cuesta-Lazaro, Carolina Mishra-Sharma, Siddharth |
| author_facet | Akhmetzhanova, Aizhan Cuesta-Lazaro, Carolina Mishra-Sharma, Siddharth |
| contents | Current and upcoming cosmological surveys will produce unprecedented amounts of high-dimensional data, which require complex high-fidelity forward simulations to accurately model both physical processes and systematic effects which describe the data generation process. However, validating whether our theoretical models accurately describe the observed datasets remains a fundamental challenge. An additional complexity to this task comes from choosing appropriate representations of the data which retain all the relevant cosmological information, while reducing the dimensionality of the original dataset. In this work we present a novel framework combining scale-dependent neural summary statistics with normalizing flows to detect model misspecification in cosmological simulations through Bayesian evidence estimation. By conditioning our neural network models for data compression and evidence estimation on the smoothing scale, we systematically identify where theoretical models break down in a data-driven manner. We demonstrate a first application to our approach using matter and gas density fields from three CAMELS simulation suites with different subgrid physics implementations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_05744 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Detecting Model Misspecification in Cosmology with Scale-Dependent Normalizing Flows Akhmetzhanova, Aizhan Cuesta-Lazaro, Carolina Mishra-Sharma, Siddharth Cosmology and Nongalactic Astrophysics Instrumentation and Methods for Astrophysics Machine Learning Current and upcoming cosmological surveys will produce unprecedented amounts of high-dimensional data, which require complex high-fidelity forward simulations to accurately model both physical processes and systematic effects which describe the data generation process. However, validating whether our theoretical models accurately describe the observed datasets remains a fundamental challenge. An additional complexity to this task comes from choosing appropriate representations of the data which retain all the relevant cosmological information, while reducing the dimensionality of the original dataset. In this work we present a novel framework combining scale-dependent neural summary statistics with normalizing flows to detect model misspecification in cosmological simulations through Bayesian evidence estimation. By conditioning our neural network models for data compression and evidence estimation on the smoothing scale, we systematically identify where theoretical models break down in a data-driven manner. We demonstrate a first application to our approach using matter and gas density fields from three CAMELS simulation suites with different subgrid physics implementations. |
| title | Detecting Model Misspecification in Cosmology with Scale-Dependent Normalizing Flows |
| topic | Cosmology and Nongalactic Astrophysics Instrumentation and Methods for Astrophysics Machine Learning |
| url | https://arxiv.org/abs/2508.05744 |