CosmicNet I: Physics-driven implementation of neural networks within Boltzmann-Einstein solvers

Abstract

Einstein-Boltzmann Solvers (EBSs) are run on a massive scale by the cosmology community when fitting cosmological models to data. We present a new concept for speeding up such codes with neural networks. The originality of our approach stems from not substituting the whole EBS by a machine learning algorithm, but only its most problematic and least parallelizable step: the integration of perturbation equations over time. This approach offers two significant advantages: the task depends only on a subset of cosmological parameters, and it is blind to the characteristics of the experiment for which the output must be computed (for instance, redshift bins). These allow us to construct a fast and highly re-usable network. In this proof-of-concept paper, we focus on the prediction of CMB source functions, and design our networks according to physical considerations and analytical approximations. This allows us to reduce the depth and training time of the networks compared to a brute-force approach. Indeed, the calculation of the source functions using the networks is fast enough so that it is not a bottleneck in the EBS anymore. Finally, we show that their accuracy is more than sufficient for accurate MCMC parameter inference from Planck data. This paves the way for a new project, CosmicNet, aimed at gradually extending the use and the range of validity of neural networks within EBSs, and saving massive computational time in the context of cosmological parameter extraction.

arXiv comment26 pages, 20 figures Replacement: Added citations

References in corpus (14)

• Planck 2013 results. XVI. Cosmological parameters
• Efficient Computation of CMB anisotropies in closed FRW models
• Cosmological parameters from CMB and other data: a Monte-Carlo approach
• The Cosmic Linear Anisotropy Solving System (CLASS) II: Approximation schemes
• A Line of Sight Approach to Cosmic Microwave Background Anisotropies
• Euclid preparation: II. The EuclidEmulator -- A tool to compute the cosmology dependence of the nonlinear matter power spectrum
• The Damping Tail of CMB Anisotropies
• Fast cosmological parameter estimation using neural networks
• Fast and accurate CMB computations in non-flat FLRW universes
• {\sc CosmoNet}: fast cosmological parameter estimation in non-flat models using neural networks
• Efficient Evaluation of Cosmological Angular Statistics
• Beyond the traditional Line-of-Sight approach of cosmological angular statistics
• Optimal polarisation equations in FLRW universes
• Pico: Parameters for the Impatient Cosmologist

Cited by in corpus (16)

• The CosmoVerse White Paper: Addressing observational tensions in cosmology with systematics and fundamental physics
• COSMOPOWER: emulating cosmological power spectra for accelerated Bayesian inference from next-generation surveys
• Cosmological constraints from the tomographic cross-correlation of DESI Luminous Red Galaxies and Planck CMB lensing
• Parameters Estimation for the Cosmic Microwave Background with Bayesian Neural Networks
• CONNECT: A neural network based framework for emulating cosmological observables and cosmological parameter inference
• Accelerating Large-Scale-Structure data analyses by emulating Boltzmann solvers and Lagrangian Perturbation Theory
• CosmicNet II: Emulating extended cosmologies with efficient and accurate neural networks
• Kernel-Based Emulator for the 3D Matter Power Spectrum from CLASS
• Deciphering the Archaeological Record: Cosmological Imprints of Non-Minimal Dark Sectors
• Analysis of Unified Galaxy Power Spectrum Multipole Measurements
• Fast and robust Bayesian Inference using Gaussian Processes with GPry
• Non-parametric reconstruction of cosmological observables using Gaussian Processes Regression
• How do we optimally sample model grids of exoplanet spectra?
• Cosmological gravity on all scales IV: 3x2pt Fisher forecasts for pixelised phenomenological modified gravity
• Neural Network Acceleration of Large-scale Structure Theory Calculations
• On the accuracy of posterior recovery with neural network emulators