A representation learning approach to probe for dynamical dark energy in matter power spectra

Abstract

We present DE-VAE, a variational autoencoder (VAE) architecture to search for a compressed representation of dynamical dark energy (DE) models in observational studies of the cosmic large-scale structure. DE-VAE is trained on matter power spectra boosts generated at wavenumbers $k\in (0.01-2.5)h/\mathrm{Mpc}$ and at four redshift values $z\in (0.1,0.48,0.78,1.5)$ for the most typical dynamical DE parametrization with two extra parameters describing an evolving DE equation of state. The boosts are compressed to a lower-dimensional representation, which is concatenated with standard cold dark matter (CDM) parameters and then mapped back to reconstructed boosts; both the compression and the reconstruction components are parametrized as neural networks. Remarkably, we find that a single latent parameter is sufficient to predict 95% (99%) of DE power spectra generated over a broad range of cosmological parameters within $1\sigma$ ($2\sigma$) of a Gaussian error which includes cosmic variance, shot noise and systematic effects for a Stage IV-like survey. This single parameter shows a high mutual information with the two DE parameters, and these three variables can be linked together with an explicit equation through symbolic regression. Considering a model with two latent variables only marginally improves the accuracy of the predictions, and adding a third latent variable has no significant impact on the model's performance. We discuss how the DE-VAE architecture can be extended from a proof of concept to a general framework to be employed in the search for a common lower-dimensional parametrization of a wide range of beyond-$\Lambda$CDM models and for different cosmological datasets. Such a framework could then both inform the development of cosmological surveys by targeting optimal probes, and provide theoretical insight into the common phenomenological aspects of beyond-$\Lambda$CDM models.

11 pages, 5 figures. Minor changes to match version published in PRD

References in corpus (14)

• Dynamics of dark energy
• The Confrontation between General Relativity and Experiment
• Models of f(R) Cosmic Acceleration that Evade Solar-System Tests
• Beyond the Cosmological Standard Model
• Test of the Equivalence Principle Using a Rotating Torsion Balance
• A Parameterized Post-Friedmann Framework for Modified Gravity
• Measuring the dark side (with weak lensing)
• A discriminating probe of gravity at cosmological scales
• Distinguishing Modified Gravity from Dark Energy
• Current constraints on the cosmic growth history
• How to optimally parametrize deviations from General Relativity in the evolution of cosmological perturbations
• On the road to percent accuracy IV: ReACT -- computing the non-linear power spectrum beyond $\Lambda$CDM
• CosmoPower-JAX: high-dimensional Bayesian inference with differentiable cosmological emulators
• Mapping the Diversity of Galaxy Spectra with Deep Unsupervised Machine Learning

Cited by in corpus (5)

• $\Lambda$CDM and early dark energy in latent space: a data-driven parametrization of the CMB temperature power spectrum
• Data-Space Validation of High-Dimensional Models by Comparing Sample Quantiles
• One latent to fit them all: a unified representation of baryonic feedback on matter distribution
• Conditional variational autoencoders for cosmological model discrimination and anomaly detection in cosmic microwave background power spectra
• Interpretability of deep-learning methods applied to large-scale structure surveys