A Framework for Obtaining Accurate Posteriors of Strong Gravitational Lensing Parameters with Flexible Priors and Implicit Likelihoods using Density Estimation

Abstract

We report the application of implicit likelihood inference to the prediction of the macro-parameters of strong lensing systems with neural networks. This allows us to perform deep learning analysis of lensing systems within a well-defined Bayesian statistical framework to explicitly impose desired priors on lensing variables, to obtain accurate posteriors, and to guarantee convergence to the optimal posterior in the limit of perfect performance. We train neural networks to perform a regression task to produce point estimates of lensing parameters. We then interpret these estimates as compressed statistics in our inference setup and model their likelihood function using mixture density networks. We compare our results with those of approximate Bayesian neural networks, discuss their significance, and point to future directions. Based on a test set of 100,000 strong lensing simulations, our amortized model produces accurate posteriors for any arbitrary confidence interval, with a maximum percentage deviation of $1.4\%$ at $21.8\%$ confidence level, without the need for any added calibration procedure. In total, inferring 100,000 different posteriors takes a day on a single GPU, showing that the method scales well to the thousands of lenses expected to be discovered by upcoming sky surveys.

Accepted for publication in The Astrophysical Journal, 17 pages, 11 figures

References in corpus (6)

• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• Fast likelihood-free cosmology with neural density estimators and active learning
• Uncertainties in Parameters Estimated with Neural Networks: Application to Strong Gravitational Lensing
• Mining for Dark Matter Substructure: Inferring subhalo population properties from strong lenses with machine learning
• Large-Scale Gravitational Lens Modeling with Bayesian Neural Networks for Accurate and Precise Inference of the Hubble Constant
• Correlated Read Noise Reduction in Infrared Arrays Using Deep Learning

Cited by in corpus (12)

• The CosmoVerse White Paper: Addressing observational tensions in cosmology with systematics and fundamental physics
• Gravitational lensing of a Schwarzschild-like black hole in Kalb-Ramond gravity
• Gravitational lens effect of a holonomy corrected Schwarzschild black hole
• Strong lensing selection effects
• Beyond Gaussian Noise: A Generalized Approach to Likelihood Analysis with non-Gaussian Noise
• Stochastic Modelling of Star Formation Histories III. Constraints from Physically-Motivated Gaussian Processes
• Scalable inference with Autoregressive Neural Ratio Estimation
• Simulation-based Inference for Gravitational-waves from Intermediate-Mass Binary Black Holes in Real Noise
• Lens Modeling of STRIDES Strongly Lensed Quasars using Neural Posterior Estimation
• Gaussian Processes and Nested Sampling Applied to Kepler's Small Long-period Exoplanet Candidates
• Deep inference of simulated strong lenses in ground-based surveys
• Predicting Sunyaev-Zel'dovich effect observations of galaxy cluster cavities with the Square Kilometre Array