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

arXiv:2510.27086 · astro-ph.CO, astro-ph.IM, gr-qc, hep-ph · Submitted 2025-10-31 · Read on arXiv

astro-ph.CO, astro-ph.IM, gr-qc, hep-ph

Submitted: 2025-10-31

Updated: 2026-08-10

Comments: 22 pages, 18 figures; accepted for publication in Physical Review D

Journal ref: Phys. Rev. D 114, 043547 (2026)

DOI: 10.1103/b4kr-srbk

License: http://creativecommons.org/licenses/by/4.0/

The gist: The cosmic microwave background power spectra are a primary window into the early universe.

Terminology

Abstract

The cosmic microwave background power spectra are a primary window into the early universe. However, achieving interpretable compression and fast inference diagnostics 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 retaining an interface to likelihood-style diagnostic tests. The model achieves high directional reconstruction fidelity for the D TT, D EE, and D TE spectra in just 5 latent dimensions. It reconstructs spectra for several beyond- Λ CDM test cases, including controlled parameter extrapolations, and enables an amortized surrogate diagnostic that reduces one representative post-training MCMC run from about 40 hours on CPU cores to about 2 minutes on a GPU in this demonstration. The learned latent space shows a distributed, partially structured organization that mirrors known cosmological parameters and their degeneracies. It also provides representation-space discrimination diagnostics for distinguishing tested cosmological spectra from a fiducial reference. Overall, this physics-informed CVAE supports interpretable compression, rapid diagnostic exploration, and anomaly-sensitive representation learning beyond Λ CDM.

Sources

Related papers