MadEvolve: Evolutionary Optimization of Cosmological Algorithms with Large Language Models
This work addresses the need for automated algorithm optimization in computational cosmology, offering a tool that enhances specific scientific tasks, though it is incremental as it builds on existing evolutionary optimization concepts.
The authors tackled the problem of discovering scientific algorithms for computational cosmology by developing MadEvolve, a framework that evolves baseline human algorithms through iterative code changes, resulting in substantial improvements over base algorithms in tasks like cosmological initial conditions reconstruction, 21cm foreground contamination reconstruction, and effective baryonic physics in N-body simulations.
We develop a general framework to discover scientific algorithms and apply it to three problems in computational cosmology. Our code, MadEvolve, is similar to Google's AlphaEvolve, but places a stronger emphasis on free parameters and their optimization. Our code starts with a baseline human algorithm implementation, and then optimizes its performance metrics by making iterative changes to its code. As a further convenient feature, MadEvolve automatically generates a report that compares the input algorithm with the evolved algorithm, describes the algorithmic innovations and lists the free parameters and their function. Our code supports both auto-differentiable, gradient-based parameter optimization and gradient-free optimization methods. We apply MadEvolve to the reconstruction of cosmological initial conditions, 21cm foreground contamination reconstruction and effective baryonic physics in N-body simulations. In all cases, we find substantial improvements over the base algorithm. We make MadEvolve and our three tasks publicly available at madevolve.org.