arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.18005math.COcs.LG
收藏

基于流的极值数学结构发现

Flow-based Extremal Mathematical Structure Discovery

Aarhus University, Denmark(奥胡斯大学,丹麦);Max Planck Institute for Mathematics in the Sciences, Leipzig, Germany(马克斯·普朗克数学研究所,莱比锡,德国)

Gergely Bérczi, Baran Hashemi, Jonas Klüver

AI总结:

FlowBoost通过闭环生成框架结合流匹配模型、奖励引导策略优化和随机局部搜索,有效发现极值几何结构,减少训练资源和时间,超越现有方法。

摘要:

数学中极值结构的发现需要在广阔而非凸的景观中导航,其中分析方法提供很少的指导,而暴力搜索变得不可行。我们介绍了FlowBoost,一种闭环生成框架,通过结合三个组件来学习发现罕见和极值几何结构:(i) 一种几何意识的条件流匹配模型,学习生成高质量的配置;(ii) 奖励引导的策略优化与动作探索,直接优化生成过程以实现目标,同时保持多样性;(iii) 随机局部搜索,用于训练数据生成和最终优化。与之前的开环方法不同,如PatternBoost重新训练于过滤后的离散样本,或AlphaEvolve依赖冻结的大型语言模型(LLMs)作为进化突变操作符,FlowBoost在采样过程中强制几何可行性,并将奖励信号直接传递到生成模型,关闭优化回路,需要更小的训练集和更短的训练时间,并将所需的外环迭代次数减少多个数量级,同时消除对LLMs的依赖。我们在四个几何优化问题上展示了该框架:超立方体中的球体排列、最大化半径和的圆排列、Heilbronn三角形问题以及星形偏差最小化。在某些情况下,FlowBoost发现了与最佳已知结果相匹配或超过的配置。对于圆排列,我们提高了最佳已知下界,超越了基于LLM的系统AlphaEvolve,同时使用了显著更少的计算资源。

英文摘要:

The discovery of extremal structures in mathematics requires navigating vast and nonconvex landscapes where analytical methods offer little guidance and brute-force search becomes intractable. We introduce FlowBoost, a closed-loop generative framework that learns to discover rare and extremal geometric structures by combining three components: (i) a geometry-aware conditional flow-matching model that learns to sample high-quality configurations, (ii) reward-guided policy optimization with action exploration that directly optimizes the generation process toward the objective while maintaining diversity, and (iii) stochastic local search for both training-data generation and final refinement. Unlike prior open-loop approaches, such as PatternBoost that retrains on filtered discrete samples, or AlphaEvolve which relies on frozen Large Language Models (LLMs) as evolutionary mutation operators, FlowBoost enforces geometric feasibility during sampling, and propagates reward signal directly into the generative model, closing the optimization loop and requiring much smaller training sets and shorter training times, and reducing the required outer-loop iterations by orders of magnitude, while eliminating dependence on LLMs. We demonstrate the framework on four geometric optimization problems: sphere packing in hypercubes, circle packing maximizing sum of radii, the Heilbronn triangle problem, and star discrepancy minimization. In several cases, FlowBoost discovers configurations that match or exceed the best known results. For circle packings, we improve the best known lower bounds, surpassing the LLM-based system AlphaEvolve while using substantially fewer computational resources.

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。

↑