Fast cosmological parameter estimation using neural networks

Abstract

We present a method for accelerating the calculation of CMB power spectra, matter power spectra and likelihood functions for use in cosmological parameter estimation. The algorithm, called CosmoNet, is based on training a multilayer perceptron neural network and shares all the advantages of the recently released Pico algorithm of Fendt & Wandelt, but has several additional benefits in terms of simplicity, computational speed, memory requirements and ease of training. We demonstrate the capabilities of CosmoNet by computing CMB power spectra over a box in the parameter space of flat ΛCDM models containing the 3σWMAP1 confidence region. We also use CosmoNet to compute the WMAP3 likelihood for flat ΛCDM models and show that marginalised posteriors on parameters derived are very similar to those obtained using CAMB and the WMAP3 code. We find that the average error in the power spectra is typically 2-3% of cosmic variance, and that CosmoNet is \sim 7 \times 10^4 faster than CAMB (for flat models) and \sim 6 \times 10^6 times faster than the official WMAP3 likelihood code. CosmoNet and an interface to CosmoMC are publically available at www.mrao.cam.ac.uk/software/cosmonet.

5 pages, 5 figures, minor changes to match version accepted by MNRAS letters

References in corpus (13)

• Efficient Computation of CMB anisotropies in closed FRW models
• First Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Preliminary Maps and Basic Results
• Cosmological parameters from CMB and other data: a Monte-Carlo approach
• A Line of Sight Approach to Cosmic Microwave Background Anisotropies
• Efficient Cosmological Parameter Estimation from Microwave Background Anisotropies
• II: Bayesian Methods for Cosmological Parameter Estimation from Cosmic Microwave Background Measurements
• Photometric redshifts with the Multilayer Perceptron Neural Network: application to the HDF-S and SDSS
• Current cosmological constraints from a 10 parameter CMB analysis
• The Age of the Universe and the Cosmological Constant Determined from Cosmic Microwave Background Anisotropy Measurements
• The entropic prior for distributions with positive and negative values
• Rapid Calculation of Theoretical CMB Angular Power Spectra
• Fast Cosmological Parameter Estimation from Microwave Background Temperature and Polarization Power Spectra
• CMBfit: Rapid WMAP likelihood calculations with normal parameters

Cited by in corpus (58)

• Comparison of decision tree methods for finding active objects
• The CosmoVerse White Paper: Addressing observational tensions in cosmology with systematics and fundamental physics
• The Coyote Universe II: Cosmological Models and Precision Emulation of the Nonlinear Matter Power Spectrum
• COSMOPOWER: emulating cosmological power spectra for accelerated Bayesian inference from next-generation surveys
• Cosmic Calibration: Constraints from the Matter Power Spectrum and the Cosmic Microwave Background
• SKYNET: an efficient and robust neural network training tool for machine learning in astronomy
• Estimation of cosmological parameters using adaptive importance sampling
• Cosmological Reconstruction From Galaxy Light: Neural Network Based Light-Matter Connection
• Estimation of Primordial Spectrum with post-WMAP 3 year data
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• {\sc CosmoNet}: fast cosmological parameter estimation in non-flat models using neural networks
• Efficient Cosmological Parameter Estimation with Hamiltonian Monte Carlo
• PkANN - II. A non-linear matter power spectrum interpolator developed using artificial neural networks
• CONNECT: A neural network based framework for emulating cosmological observables and cosmological parameter inference
• Convolutional Neural Networks on the HEALPix sphere: a pixel-based algorithm and its application to CMB data analysis
• PkANN - I. Non-linear matter power spectrum interpolation through artificial neural networks
• A Coverage Study of the CMSSM Based on ATLAS Sensitivity Using Fast Neural Networks Techniques
• Accelerating Large-Scale-Structure data analyses by emulating Boltzmann solvers and Lagrangian Perturbation Theory
• BAMBI: blind accelerated multimodal Bayesian inference
• CosmicNet II: Emulating extended cosmologies with efficient and accurate neural networks
• Kernel-Based Emulator for the 3D Matter Power Spectrum from CLASS
• Machine Learning for Observational Cosmology
• ECoPANN: A Framework for Estimating Cosmological Parameters using Artificial Neural Networks
• Neural network reconstructions for the Hubble parameter, growth rate and distance modulus
• Capse.jl: efficient and auto-differentiable CMB power spectra emulation
• Cosmological parameter estimation using Particle Swarm Optimization (PSO)
• Deciphering the Archaeological Record: Cosmological Imprints of Non-Minimal Dark Sectors
• Simulations and cosmological inference: A statistical model for power spectra means and covariances
• Neural Network Reconstruction of $H^{\prime }(z)$ and its application in Teleparallel Gravity
• Observational cosmology with Artificial Neural Networks
• CosmicNet I: Physics-driven implementation of neural networks within Boltzmann-Einstein solvers
• Parameter Inference for Weak Lensing using Gaussian Processes and MOPED
• Intelligent Design: On the Emulation of Cosmological Simulations
• CMB likelihood approximation by a Gaussianized Blackwell-Rao estimator
• Profile Likelihoods in Cosmology: When, Why and How illustrated with $\Lambda$CDM, Massive Neutrinos and Dark Energy
• Fast and robust Bayesian Inference using Gaussian Processes with GPry
• Fast supersymmetry phenomenology at the Large Hadron Collider using machine learning techniques
• Inferring galaxy dark halo properties from visible matter with Machine Learning
• LINNA: Likelihood Inference Neural Network Accelerator
• Gradient boosting decision trees classification of blazars of uncertain type in the fourth Fermi-LAT catalog
• Accelerating cosmological inference with Gaussian processes and neural networks -- an application to LSST Y1 weak lensing and galaxy clustering
• Accelerating Bayesian microseismic event location with deep learning
• Foreground removal from CMB temperature maps using an MLP neural network
• Towards fast machine-learning-assisted Bayesian posterior inference of microseismic event location and source mechanism
• Optimising Boltzmann codes for the Planck era
• Deep Learning and genetic algorithms for cosmological Bayesian inference speed-up
• Efficient cosmological parameter sampling using sparse grids
• Learn-As-You-Go Acceleration of Cosmological Parameter Estimates
• Exploring local fNL estimators based on the binned bispectrum
• MF-Box: Multi-fidelity and multi-scale emulation for the matter power spectrum
• Grid-based exploration of cosmological parameter space with Snake
• Constraints on fNL from Wilkinson Microwave Anisotropy Probe 7-year data using a neural network classifier
• Cosmological gravity on all scales IV: 3x2pt Fisher forecasts for pixelised phenomenological modified gravity
• Cosmic Kite: Auto-encoding the Cosmic Microwave Background
• DeepSSM: an emulator of gravitational wave spectra from sound waves during cosmological first-order phase transitions
• Design and optimization of neural networks for multifidelity cosmological emulation
• On the accuracy of posterior recovery with neural network emulators
• Using Statistical Emulation and Knowledge of Grain-Surface Diffusion for Bayesian Inference of Reaction Rate Parameters: An Application to a Glycine Network