Cosmological Parameter Estimation and Inference using Deep Summaries

Abstract

The ability to obtain reliable point estimates of model parameters is of crucial importance in many fields of physics. This is often a difficult task given that the observed data can have a very high number of dimensions. In order to address this problem, we propose a novel approach to construct parameter estimators with a quantifiable bias using an order expansion of highly compressed deep summary statistics of the observed data. These summary statistics are learned automatically using an information maximising loss. Given an observation, we further show how one can use the constructed estimators to obtain approximate Bayes computation (ABC) posterior estimates and their corresponding uncertainties that can be used for parameter inference using Gaussian process regression even if the likelihood is not tractable. We validate our method with an application to the problem of cosmological parameter inference of weak lensing mass maps. We show in that case that the constructed estimators are unbiased and have an almost optimal variance, while the posterior distribution obtained with the Gaussian process regression is close to the true posterior and performs better or equally well than comparable methods.

18 pages, 10 figures

References in corpus (10)

• Weight Uncertainty in Neural Networks
• Dark Energy Survey Year 3 Results: Cosmology from Cosmic Shear and Robustness to Modeling Uncertainty
• GPflow: A Gaussian process library using TensorFlow
• Fast likelihood-free cosmology with neural density estimators and active learning
• Optimal Surveys for Weak Lensing Tomography
• Nuisance hardened data compression for fast likelihood-free inference
• Lossless, Scalable Implicit Likelihood Inference for Cosmological Fields
• Neural networks as optimal estimators to marginalize over baryonic effects
• Neural Approximate Sufficient Statistics for Implicit Models
• Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian Computation

Cited by in corpus (10)

• A Full $w$CDM Analysis of KiDS-1000 Weak Lensing Maps using Deep Learning
• The Cosmic Graph: Optimal Information Extraction from Large-Scale Structure using Catalogues
• CosmoGridV1: a simulated $w$CDM theory prediction for map-level cosmological inference
• EFTofLSS meets simulation-based inference: ${\sigma }_8$ from biased tracers
• Machine Learning and Cosmology
• Forecasting the power of Higher Order Weak Lensing Statistics with automatically differentiable simulations
• A tomographic spherical mass map emulator of the KiDS-1000 survey using conditional generative adversarial networks
• Full-waveform earthquake source inversion using simulation-based inference
• CLAP. I. Resolving miscalibration for deep learning-based galaxy photometric redshift estimation
• Simulation-based inference has its own Dodelson-Schneider effect (but it knows that it does)