AI4SLT: 基于 Lean 4 的形式化统计学习理论实证过程
AI4SLT: Empirical Processes in Lean 4 for Formal Statistical Learning Theory
AI总结:
本文首次在 Lean 4 中完整形式化统计学习理论,基于实证过程理论,通过人机协作工作流构建了可验证的定理证明工具箱,并揭示了教材中的隐含假设。
摘要:
我们提出了首个基于实证过程理论的统计学习理论(SLT)在 Lean 4 中的全面形式化。我们的端到端形式化基础设施填补了最新 Lean 库中缺失的内容,包括高斯 Lipschitz 集中的完整推导、次高斯过程的 Dudley 熵积分定理,以及具有尖锐速率的(稀疏)最小二乘回归应用。该项目采用人机协作工作流,其中人类设计证明策略,AI 代理执行战术性证明构建,从而产生了经过人工验证的 SLT 的 Lean 4 工具箱。除了实现之外,形式化过程暴露并解决了标准 SLT 教材中的隐含假设和缺失细节,强制对理论进行逐行细粒度理解。这项工作建立了一个可重用的形式化基础,并为机器学习理论的未来发展打开了大门。代码可在以下网址获取:https://this https URL。
英文摘要:
We present the first comprehensive Lean 4 formalization of statistical learning theory (SLT) grounded in empirical process theory. Our en-to-end formal infrastructure implement the missing contents in latest Lean library, including a complete development of Gaussian Lipschitz concentration, Dudley's entropy integral theorem for sub-Gaussian processes, and an application to least-squares (sparse) regression with a sharp rate. The project was carried out using a human-AI collaborative workflow, in which humans design proof strategies and AI agents execute tactical proof construction, leading to the human-verified Lean 4 toolbox for SLT. Beyond implementation, the formalization process exposes and resolves implicit assumptions and missing details in standard SLT textbooks, enforcing a granular, line-by-line understanding of the theory. This work establishes a reusable formal foundation and opens the door for future developments in machine learning theory. The code is provided in https://github.com/YuanheZ/lean-stat-learning-theory.
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。