arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.15951astro-ph.COcs.LG
收藏

MadEvolve:利用大语言模型进行宇宙学算法的进化优化

MadEvolve: Evolutionary Optimization of Cosmological Algorithms with Large Language Models

University of Wisconsin-Madison(威斯康星大学麦迪逊分校)

Tianyi Li, Shihui Zang, Moritz Münchmeyer

AI总结:

MadEvolve利用大语言模型优化宇宙学算法,通过进化方法提升计算性能并公开相关任务。

摘要:

我们开发了一个通用框架来发现科学算法,并将其应用于计算宇宙学中的三个问题。我们的代码MadEvolve类似于谷歌的AlphaEvolve,但更强调自由参数及其优化。我们的代码从基线人工算法实现开始,然后通过不断修改其代码来优化其性能指标。作为进一步的便利功能,MadEvolve会自动生成一份报告,比较输入算法与进化后的算法,描述算法创新并列出自由参数及其功能。我们的代码支持自动可微、基于梯度的参数优化和无梯度优化方法。我们应用MadEvolve到宇宙学初始条件的重建、21cm前景污染重建以及N体模拟中的有效等离子体物理。在所有情况下,我们发现相对于基线算法有显著的改进。我们将在madevolve.org上公开MadEvolve和我们的三个任务。

英文摘要:

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.

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。

↑