CONNECT: A neural network based framework for emulating cosmological observables and cosmological parameter inference

Abstract

Bayesian parameter inference is an essential tool in modern cosmology, and typically requires the calculation of $10^5$--$10^6$ theoretical models for each inference of model parameters for a given dataset combination. Computing these models by solving the linearised Einstein-Boltzmann system usually takes tens of CPU core-seconds per model, making the entire process very computationally expensive. In this paper we present \textsc{connect}, a neural network framework emulating \textsc{class} computations as an easy-to-use plug-in for the popular sampler \textsc{MontePython}. \textsc{connect} uses an iteratively trained neural network which emulates the observables usually computed by \textsc{class}. The training data is generated using \textsc{class}, but using a novel algorithm for generating favourable points in parameter space for training data, the required number of \textsc{class}-evaluations can be reduced by two orders of magnitude compared to a traditional inference run. Once \textsc{connect} has been trained for a given model, no additional training is required for different dataset combinations, making \textsc{connect} many orders of magnitude faster than \textsc{class} (and making the inference process entirely dominated by the speed of the likelihood calculation). For the models investigated in this paper we find that cosmological parameter inference run with \textsc{connect} produces posteriors which differ from the posteriors derived using \textsc{class} by typically less than $0.01$--$0.1$ standard deviations for all parameters. We also stress that the training data can be produced in parallel, making efficient use of all available compute resources. The \textsc{connect} code is publicly available for download at \url{https://github.com/AarhusCosmology}.

27 pages, 14 figures - Revision after submission to JCAP

References in corpus (18)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Cobaya: Code for Bayesian Analysis of hierarchical physical models
• Bayesian Neural Networks: An Introduction and Survey
• COSMOPOWER: emulating cosmological power spectra for accelerated Bayesian inference from next-generation surveys
• Euclid preparation: IX. EuclidEmulator2 -- Power spectrum emulation with massive neutrinos and self-consistent dark energy perturbations
• Fast cosmological parameter estimation using neural networks
• {\sc CosmoNet}: fast cosmological parameter estimation in non-flat models using neural networks
• Efficient Cosmological Parameter Estimation with Hamiltonian Monte Carlo
• Updated constraints on decaying cold dark matter
• Accelerating Large-Scale-Structure data analyses by emulating Boltzmann solvers and Lagrangian Perturbation Theory
• Cosmological parameter estimation via iterative emulation of likelihoods
• CosmicNet II: Emulating extended cosmologies with efficient and accurate neural networks
• Kernel-Based Emulator for the 3D Matter Power Spectrum from CLASS
• ECoPANN: A Framework for Estimating Cosmological Parameters using Artificial Neural Networks
• Multi-Fidelity Emulation for the Matter Power Spectrum using Gaussian Processes
• Fast and robust Bayesian Inference using Gaussian Processes with GPry
• LINNA: Likelihood Inference Neural Network Accelerator
• Accelerating cosmological inference with Gaussian processes and neural networks -- an application to LSST Y1 weak lensing and galaxy clustering

Cited by in corpus (24)

• The CosmoVerse White Paper: Addressing observational tensions in cosmology with systematics and fundamental physics
• $\Lambda$CDM Tensions: Localising Missing Physics through Consistency Checks
• CosmicNet II: Emulating extended cosmologies with efficient and accurate neural networks
• Capse.jl: efficient and auto-differentiable CMB power spectra emulation
• Cosmological parameter estimation with Genetic Algorithms
• candl: Cosmic Microwave Background Analysis with a Differentiable Likelihood
• Profile Likelihoods in Cosmology: When, Why and How illustrated with $\Lambda$CDM, Massive Neutrinos and Dark Energy
• Analysis of Unified Galaxy Power Spectrum Multipole Measurements
• Fast and robust Bayesian Inference using Gaussian Processes with GPry
• A neural network emulator for the Lyman-$\alpha$ 1D flux power spectrum
• Non-parametric reconstruction of cosmological observables using Gaussian Processes Regression
• Fast and effortless computation of profile likelihoods using CONNECT
• Fast likelihood-free inference in the LSS Stage IV era
• Deep Learning and genetic algorithms for cosmological Bayesian inference speed-up
• Faster Bayesian inference with neural network bundles and new results for $f(R)$ models
• Neutrino decays as a natural explanation of the neutrino mass tension
• Calculating Bayesian evidence for inflationary models using CONNECT
• DeepSSM: an emulator of gravitational wave spectra from sound waves during cosmological first-order phase transitions
• Constraining the primordial power spectrum using a differentiable likelihood
• Constraining Galaxy-Halo Connection Using Machine Learning
• Parameter estimation from Ly$\alpha$ forest in Fourier space using Information Maximising Neural Network
• Design and optimization of neural networks for multifidelity cosmological emulation
• ABCMB: A Python+JAX Package for the Cosmic Microwave Background Power Spectrum
• How to embed any likelihood into SBI: Application to Planck + Stage IV galaxy surveys and Dynamical Dark Energy