Likelihood-free Inference with Mixture Density Network

Abstract

In this work, we propose using the mixture density network (MDN) to estimate cosmological parameters. We test the MDN method by constraining parameters of the $\Lambda$CDM and $w$CDM models using Type Ia supernovae and the power spectra of the cosmic microwave background. We find that the MDN method can achieve the same level of accuracy as the Markov Chain Monte Carlo method, with a slight difference of $\mathcal{O}(10^{-2}\sigma )$. Furthermore, the MDN method can provide accurate parameter estimates with $\mathcal{O}(10^3)$ forward simulation samples, which are useful for complex and resource-consuming cosmological models. This method can process either one data set or multiple data sets to achieve joint constraints on parameters, extendable for any parameter estimation of complicated models in a wider scientific field. Thus, the MDN provides an alternative way for likelihood-free inference of parameters.

17 pages, 4 tables, 15 figures, match the published version. The code repository is available at https://github.com/Guo-Jian-Wang/mdncoper

References in corpus (39)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• emcee: The MCMC Hammer
• The cosmological simulation code GADGET-2
• The Complete Light-curve Sample of Spectroscopically Confirmed Type Ia Supernovae from Pan-STARRS1 and Cosmological Constraints from The Combined Pantheon Sample
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Wide-Field InfrarRed Survey Telescope-Astrophysics Focused Telescope Assets WFIRST-AFTA 2015 Report
• Halos and galaxies in the standard cosmological model: results from the Bolshoi simulation
• Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
• Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• Fast likelihood-free cosmology with neural density estimators and active learning
• Finding Strong Gravitational Lenses in the Kilo Degree Survey with Convolutional Neural Networks
• Deep Transfer Learning: A new deep learning glitch classification method for advanced LIGO
• Glitch Classification and Clustering for LIGO with Deep Transfer Learning
• Massive optimal data compression and density estimation for scalable, likelihood-free inference in cosmology
• Cosmological constraints with deep learning from KiDS-450 weak lensing maps
• Finding strong lenses in CFHTLS using convolutional neural networks
• The Evolution of 21-cm Structure (EOS): public, large-scale simulations of Cosmic Dawn and Reionization
• Emulating Simulations of Cosmic Dawn for 21cm Power Spectrum Constraints on Cosmology, Reionization, and X-ray Heating
• A deep learning approach to cosmological dark energy models
• Weak lensing cosmology with convolutional neural networks on noisy data
• Analysing the 21cm signal from the Epoch of Reionization with artificial neural networks
• Reconstructing Functions and Estimating Parameters with Artificial Neural Networks: A Test with the Hubble Parameter and SNe Ia
• Emulation of reionization simulations for Bayesian inference of astrophysics parameters using neural networks
• Deep Convolutional Neural Networks as strong gravitational lens detectors
• Cosmological constraints from noisy convergence maps through deep learning
• New high-quality strong lens candidates with deep learning in the Kilo Degree Survey
• LensExtractor: A Convolutional Neural Network in Search of Strong Gravitational Lenses
• Simulation-Based Inference of Reionization Parameters From 3D Tomographic 21 cm Lightcone Images
• High-quality strong lens candidates in the final Kilo Degree survey footprint
• Classifying the Large Scale Structure of the Universe with Deep Neural Networks
• Full-sky Cosmic Microwave Background Foreground Cleaning Using Machine Learning
• Some Optimizations on Detecting Gravitational Wave Using Convolutional Neural Network
• Machine Learning the Cosmic Curvature in a Model-independent Way
• A Hybrid Deep Learning Approach to Cosmological Constraints From Galaxy Redshift Surveys
• ECoPANN: A Framework for Estimating Cosmological Parameters using Artificial Neural Networks
• Recovering the CMB Signal with Machine Learning
• Technical report: Training Mixture Density Networks with full covariance matrices
• Reionization Models Classifier using 21cm Map Deep Learning

Cited by in corpus (7)

• Galaxy morphoto-Z with neural Networks (GaZNets). I. Optimized accuracy and outlier fraction from Imaging and Photometry
• CoLFI: Cosmological Likelihood-free Inference with Neural Density Estimators
• In search of an interaction in the dark sector through Gaussian Process and ANN approaches
• SIDE-real: Supernova Ia Dust Extinction with truncated marginal neural ratio estimation applied to real data
• Observational constraints using Bayesian statistics and Deep Learning in $f(Q)$ gravity
• STAR NRE: Solving supernova selection effects with set-based truncated auto-regressive neural ratio estimation
• Constraining primordial non-Gaussianity using Neural Networks