研究人员为核梯度流和无穷小梯度提升建立了函数中心极限定理。该定理详述了该过程围绕其确定性极限的波动，显示出向高斯过程的收敛。分析在再生核希尔伯特空间中进行，其中梯度提升过程被视为常微分方程的解。该方法涉及Banach空间中ODE的通用随机扰动分析，适用于核梯度流和更复杂的基于树的梯度提升场景。 AI
影响 为理解梯度提升方法的行为提供了理论框架，可能导致更健壮和可预测的AI模型。
排序理由 该集群包含一篇详细介绍统计机器学习新定理的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.25494v1 Announce Type: cross Abstract: Building on the large-sample analysis of infinitesimal gradient boosting (Dombry and Duchamps, 2024b), we study the fluctuations of the process around its deterministic limit and establish a functional central limit theorem: the r…
Building on the large-sample analysis of infinitesimal gradient boosting (Dombry and Duchamps, 2024b), we study the fluctuations of the process around its deterministic limit and establish a functional central limit theorem: the rescaled deviations converge in distribution to a G…