arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.05520cs.LGstat.ML
收藏

机器学习理论

A Theory of Machine Learning

Underwood International College(安德伍德国际学院);Yonsei University(延世大学);Seoul National University(首尔大学)

Jinsook Kim, Jinho Kang

AI总结:

本文批判性回顾三种机器学习理论,提出以“成功计算函数”为学习标准的新理论,挑战统计与计算学习理论的常见假设,并结合自然语言处理和宏观经济学案例加以说明。

摘要:

我们批判性地回顾了机器学习的三大主要理论,并提出一种新理论:根据该理论,当机器成功计算出某个函数时,它们就学会了该函数。我们表明,这一理论挑战了统计学习理论和计算学习理论中的常见假设,因为它意味着学习真实概率,既不等同于获得对真实概率的正确计算,也不等同于获得对其的几乎必然收敛。我们还从新理论的视角简要讨论了来自自然语言处理和宏观经济学的若干案例研究。

英文摘要:

We critically review three major theories of machine learning and provide a new theory according to which machines learn a function when the machines successfully compute it. We show that this theory challenges common assumptions in the statistical and the computational learning theories, for it implies that learning true probabilities is equivalent neither to obtaining a correct calculation of the true probabilities nor to obtaining an almost-sure convergence to them. We also briefly discuss some case studies from natural language processing and macroeconomics from the perspective of the new 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。

↑