可微强透镜:通过可微概率规划将引力和神经网络结合起来
Differentiable Strong Lensing: Uniting Gravity and Neural Nets through Differentiable Probabilistic Programming
摘要:
由于即将到来的望远镜将观测数千个强大的透镜系统,因此为这些图像创建全自动分析管道变得越来越重要。在这项工作中,我们通过开发第一个端到端可微分强透镜管道向这个方向迈出了一步。我们的方法利用并结合了三个重要的计算机科学发展:(a)卷积神经网络,(b)高效的基于梯度的采样技术,以及(c)深度概率编程语言。后者自动化参数推断,并使生成深度神经网络和物理组件在单个模型中相结合。在目前的工作中,我们证明了可以将在星系图像上训练的卷积神经网络作为源模型与引力透镜物理学的完全可微和精确实现结合在一起。这消除了源模型的超参数调整,使得能够使用基于梯度的方法同时优化近100个源和透镜参数,并且允许使用有效的基于梯度的后验采样技术。这些特性使得这种自动推理管道可能适合处理大量数据。通过分析不同信噪比的模拟透镜系统,我们表明,透镜参数的重建具有100级的精度。更一般地说,我们认为这项工作是在粒子天体物理学社区建立可微概率编程技术的第一步,它有可能显着加速和改善许多复杂的数据分析任务。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。