用大模型进化优化宇宙学算法，显著提升三类科学问题求解性能。
MadEvolve: Evolutionary Optimization of Cosmological Algorithms with Large Language Models
- 基于人类初始算法，通过迭代代码改写自动优化参数
- 在三个宇宙学问题上均实现性能显著超越基线算法
- 支持梯度与非梯度优化，自动生成对比报告与创新说明
我们开发了一个通用框架以发现科学算法，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 Google 的 AlphaEvolve，但更强调自由参数及其优化。该代码从人类编写的基准算法开始，通过迭代修改代码来优化其性能指标。此外，MadEvolve 能自动生成报告，比较输入算法与演化后的算法，描述算法创新点，并列出自由参数及其功能。代码支持可微分的梯度优化和无梯度优化方法。我们将 MadEvolve 应用于宇宙学初态重建、21cm 前景污染重建以及 N-body 模拟中的有效星系物理建模，在所有情况下均取得明显优于基线算法的性能。MadEvolve 及三个任务的代码已公开发布于 madevolve.org。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。