Differentiable Strong Lensing: Uniting Gravity and Neural Nets through Differentiable Probabilistic Programming

TL;DR

This paper introduces the first end-to-end differentiable pipeline for strong lensing analysis, combining neural networks, probabilistic programming, and physics to enable automated, accurate, and scalable parameter inference from telescope data.

Contribution

It develops a novel differentiable probabilistic model that integrates neural source modeling with gravitational physics, eliminating hyperparameter tuning and enabling gradient-based inference.

Findings

Achieves percent-level accuracy in lens parameter reconstruction

Enables simultaneous optimization of nearly 100 parameters

Demonstrates potential for processing large astronomical datasets

Abstract

Since upcoming telescopes will observe thousands of strong lensing systems, creating fully-automated analysis pipelines for these images becomes increasingly important. In this work, we make a step towards that direction by developing the first end-to-end differentiable strong lensing pipeline. Our approach leverages and combines three important computer science developments: (a) convolutional neural networks, (b) efficient gradient-based sampling techniques, and (c) deep probabilistic programming languages. The latter automatize parameter inference and enable the combination of generative deep neural networks and physics components in a single model. In the current work, we demonstrate that it is possible to combine a convolutional neural network trained on galaxy images as a source model with a fully-differentiable and exact implementation of gravitational lensing physics in a single probabilistic model. This does away with hyperparameter tuning for the source model, enables the simultaneous optimization of nearly one hundred source and lens parameters with gradient-based methods, and allows the use of efficient gradient-based posterior sampling techniques. These features make this automated inference pipeline potentially suitable for processing a large amount of data. By analyzing mock lensing systems with different signal-to-noise ratios, we show that lensing parameters are reconstructed with percent-level accuracy. More generally, we consider this work as one of the first steps in establishing differentiable probabilistic programming techniques in the particle astrophysics community, which have the potential to significantly accelerate and improve many complex data analysis tasks.