arXiv:2506.12230astro-ph.IMcs.LG2025-06被引 2

用贝叶斯框架统合天文数据中的机器学习方法,强调不确定性与统计严谨性。

Statistical Machine Learning for Astronomy -- A Textbook

  • 从概率论出发,以贝叶斯视角推导各类统计与机器学习算法
  • 覆盖线性回归、分类、主成分分析、马尔可夫链蒙特卡洛等核心方法
  • 适合需要理解算法原理的天文学研究者和数据科学家

本书系统阐述了基于贝叶斯推断的统计机器学习在天文学研究中的应用,构建了一个统一框架,揭示现代数据分析技术与传统统计方法之间的联系。通过一致的贝叶斯视角,强调不确定性量化与统计严谨性,这对天文学科学推断至关重要。内容涵盖概率论与贝叶斯推断、带测量误差的线性回归、逻辑回归与分类、主成分分析与聚类方法,以及采样与马尔可夫链蒙特卡洛计算技术。进一步介绍高斯过程作为概率非参数方法,以及神经网络在更广泛的统计背景下的定位。采用理论导向的教学方式,每种方法均从基本原理推导,注重统计洞察力,并结合天文应用实例。目标是帮助读者理解算法为何有效、何时适用,及其与统计原则的关联,最终为大型天文调查时代的科学研究提供坚实的方法论基础。

原文摘要 · Abstract (English)

This textbook provides a systematic treatment of statistical machine learning for astronomical research through the lens of Bayesian inference, developing a unified framework that reveals connections between modern data analysis techniques and traditional statistical methods. We show how these techniques emerge from familiar statistical foundations. The consistently Bayesian perspective prioritizes uncertainty quantification and statistical rigor essential for scientific inference in astronomy. The textbook progresses from probability theory and Bayesian inference through supervised learning including linear regression with measurement uncertainties, logistic regression, and classification. Unsupervised learning topics cover Principal Component Analysis and clustering methods. We then introduce computational techniques through sampling and Markov Chain Monte Carlo, followed by Gaussian Processes as probabilistic nonparametric methods and neural networks within the broader statistical context. Our theory-focused pedagogical approach derives each method from first principles with complete mathematical development, emphasizing statistical insight and complementing with astronomical applications. We prioritize understanding why algorithms work, when they are appropriate, and how they connect to broader statistical principles. The treatment builds toward modern techniques including neural networks through a solid foundation in classical methods and their theoretical underpinnings. This foundation enables thoughtful application of these methods to astronomical research, ensuring proper consideration of assumptions, limitations, and uncertainty propagation essential for advancing astronomical knowledge in the era of large astronomical surveys.

贝叶斯推断统计学习天文学机器学习

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。