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 2507.21189cs.LG
收藏

基于算子的机器智能:面向谱学习与符号推理的希尔伯特空间框架

Operator-Based Machine Intelligence: A Hilbert Space Framework for Spectral Learning and Symbolic Reasoning

UC Berkeley, School of Information(伯克利大学信息学院)

Andrew Kiruluta, Andreas Lemos, Priscilla Burity

AI总结:

该研究提出基于希尔伯特空间的机器学习替代框架,借助泛函分析等工具构建严格数学表述,介绍散射变换、Koopman算子相关模型,为可扩展、可解释的机器学习提供新方向。

摘要:

传统机器学习模型(尤其是神经网络)植根于有限维参数空间与非线性函数近似。本报告探索了一种替代范式:将学习任务表述为无限维希尔伯特空间中的采样与计算,借助泛函分析、信号处理与谱理论工具展开研究。我们回顾了再生核希尔伯特空间(RKHS)、谱算子学习、小波域表示等基础概念,给出了希尔伯特空间中学习的严格数学表述,重点介绍了基于散射变换与Koopman算子的近期模型,并讨论了其相较于传统神经架构的优势与局限。报告最后概述了基于希尔伯特信号处理的可扩展、可解释机器学习的发展方向。

英文摘要:

Traditional machine learning models, particularly neural networks, are rooted in finite-dimensional parameter spaces and nonlinear function approximations. This report explores an alternative formulation where learning tasks are expressed as sampling and computation in infinite dimensional Hilbert spaces, leveraging tools from functional analysis, signal processing, and spectral theory. We review foundational concepts such as Reproducing Kernel Hilbert Spaces (RKHS), spectral operator learning, and wavelet-domain representations. We present a rigorous mathematical formulation of learning in Hilbert spaces, highlight recent models based on scattering transforms and Koopman operators, and discuss advantages and limitations relative to conventional neural architectures. The report concludes by outlining directions for scalable and interpretable machine learning grounded in Hilbertian signal processing.

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。

↑