A Fast Generative Framework for High-dimensional Posterior Sampling: Application to CMB Delensing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914369884913664 |
|---|---|
| author | Sotoudeh, Hadi Lemos, Pablo Perreault-Levasseur, Laurence |
| author_facet | Sotoudeh, Hadi Lemos, Pablo Perreault-Levasseur, Laurence |
| contents | We introduce a deep generative framework for high-dimensional Bayesian inference that enables efficient posterior sampling. As telescopes and simulations rapidly expand the volume and resolution of astrophysical data, fast simulation-based inference methods are increasingly needed to extract scientific insights. While diffusion-based approaches offer high-quality generative capabilities, they are hindered by slow sampling speeds. Our method performs posterior sampling an order of magnitude faster than a diffusion baseline. Applied to the problem of CMB delensing, it successfully recovers the unlensed CMB power spectrum from simulated observations. The model also remains robust to shifts in cosmological parameters, demonstrating its potential for out-of-distribution generalization and application to observational cosmological data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04535 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Fast Generative Framework for High-dimensional Posterior Sampling: Application to CMB Delensing Sotoudeh, Hadi Lemos, Pablo Perreault-Levasseur, Laurence Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics Machine Learning 62F15, 68T07, 62P35 I.2.6; G.3; I.4.9 We introduce a deep generative framework for high-dimensional Bayesian inference that enables efficient posterior sampling. As telescopes and simulations rapidly expand the volume and resolution of astrophysical data, fast simulation-based inference methods are increasingly needed to extract scientific insights. While diffusion-based approaches offer high-quality generative capabilities, they are hindered by slow sampling speeds. Our method performs posterior sampling an order of magnitude faster than a diffusion baseline. Applied to the problem of CMB delensing, it successfully recovers the unlensed CMB power spectrum from simulated observations. The model also remains robust to shifts in cosmological parameters, demonstrating its potential for out-of-distribution generalization and application to observational cosmological data. |
| title | A Fast Generative Framework for High-dimensional Posterior Sampling: Application to CMB Delensing |
| topic | Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics Machine Learning 62F15, 68T07, 62P35 I.2.6; G.3; I.4.9 |
| url | https://arxiv.org/abs/2603.04535 |