Conditional variational autoencoders for cosmological model discrimination and anomaly detection in cosmic microwave background power spectra

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sun, Tian-Yang, Li, Tian-Nuo, Wang, He, Zhang, Jing-Fei, Zhang, Xin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914126649884672
author Sun, Tian-Yang
Li, Tian-Nuo
Wang, He
Zhang, Jing-Fei
Zhang, Xin
author_facet Sun, Tian-Yang
Li, Tian-Nuo
Wang, He
Zhang, Jing-Fei
Zhang, Xin
contents The cosmic microwave background power spectra are a primary window into the early universe. However, achieving interpretable, likelihood-compatible compression and fast inference under weak model assumptions remains challenging. We propose a parameter-conditioned variational autoencoder (CVAE) that aligns a data-driven latent representation with cosmological parameters while remaining compatible with standard likelihood analyses. The model achieves high-fidelity compression of the $D_\ell^{TT}$, $D_\ell^{EE}$, and $D_\ell^{TE}$ spectra into just 5 latent dimensions, with reconstruction accuracy exceeding $99.9\%$ within Planck uncertainties. It reliably reconstructs spectra for beyond-$Λ$CDM scenarios, even under parameter extrapolation, and enables rapid inference, reducing the computation time from $\sim$40 hours to $\sim$2 minutes while maintaining posterior consistency. The learned latent space demonstrates a physically meaningful structure, capturing a distributed representation that mirrors known cosmological parameters and their degeneracies. Moreover, it supports highly effective unsupervised discrimination among cosmological models, achieving performance competitive with supervised approaches. Overall, this physics-informed CVAE enables anomaly detection beyond $Λ$CDM and points to physically meaningful directions for refinement.
format Preprint
id arxiv_https___arxiv_org_abs_2510_27086
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Conditional variational autoencoders for cosmological model discrimination and anomaly detection in cosmic microwave background power spectra
Sun, Tian-Yang
Li, Tian-Nuo
Wang, He
Zhang, Jing-Fei
Zhang, Xin
Cosmology and Nongalactic Astrophysics
Instrumentation and Methods for Astrophysics
General Relativity and Quantum Cosmology
High Energy Physics - Phenomenology
The cosmic microwave background power spectra are a primary window into the early universe. However, achieving interpretable, likelihood-compatible compression and fast inference under weak model assumptions remains challenging. We propose a parameter-conditioned variational autoencoder (CVAE) that aligns a data-driven latent representation with cosmological parameters while remaining compatible with standard likelihood analyses. The model achieves high-fidelity compression of the $D_\ell^{TT}$, $D_\ell^{EE}$, and $D_\ell^{TE}$ spectra into just 5 latent dimensions, with reconstruction accuracy exceeding $99.9\%$ within Planck uncertainties. It reliably reconstructs spectra for beyond-$Λ$CDM scenarios, even under parameter extrapolation, and enables rapid inference, reducing the computation time from $\sim$40 hours to $\sim$2 minutes while maintaining posterior consistency. The learned latent space demonstrates a physically meaningful structure, capturing a distributed representation that mirrors known cosmological parameters and their degeneracies. Moreover, it supports highly effective unsupervised discrimination among cosmological models, achieving performance competitive with supervised approaches. Overall, this physics-informed CVAE enables anomaly detection beyond $Λ$CDM and points to physically meaningful directions for refinement.
title Conditional variational autoencoders for cosmological model discrimination and anomaly detection in cosmic microwave background power spectra
topic Cosmology and Nongalactic Astrophysics
Instrumentation and Methods for Astrophysics
General Relativity and Quantum Cosmology
High Energy Physics - Phenomenology
url https://arxiv.org/abs/2510.27086