AstroAI Lunch Talks - April 27, 2026 - Ludvig Doeser
27 Apr 2026 - Joshua Wing
The video can be found here: https://www.youtube.com/watch?v=2bdLB6xeWgg
Speaker: Ludvig Doeser (Stockholm/Flatiron)
Title: Towards Next-Generation Cosmic Digital Twins with Deep Learning
Abstract: Traditional gradient-based optimization and statistical inference methods often rely on differentiable models, making it challenging to optimize models with non-differentiable components. In this talk, I’ll introduce Learning the Universe by Learning to Optimize (LULO), a novel deep learning-based framework designed to fit non-differentiable simulators at non-linear scales to data. By employing a neural optimizer in an iterative scheme while keeping full physics simulations in the loop, LULO ensures both scalability and reliability. In particular, I will demonstrate how LULO accurately reconstructs the 3D cosmological initial conditions and corresponding late-time structures from mock data generated by a non-differentiable and non-linear simulator pipeline. Our method provides a promising path forward for performing detailed field-level inference with next-generation galaxy clustering survey data, without the need for differentiable models.