跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2602.02190 · v3

PCA of probability measures: Sparse and Dense sampling regimes

首次提交 2026-02-02 22:56
版本更新 2026-11-17 00:26
雷达观测 2026-11-17 16:10
arXiv ↗PDF ↗

摘要

A common approach to perform PCA on probability measures is to embed them into a Hilbert space where standard functional PCA techniques apply. While convergence rates for estimating the embedding of a single measure from mm samples are well understood, the literature has not addressed the setting involving multiple measures. In this paper, we study PCA in a double asymptotic regime where nn probability measures are observed, each through mm samples. We derive convergence rates of the form n−1/2+m−αn^{-1/2} + m^{-α} for the empirical covariance operator and the PCA excess risk, where α>0α>0 depends on the chosen embedding. This characterizes the relationship between the number nn of measures and the number mm of samples per measure, revealing a sparse (small mm) to dense (large mm) transition in the convergence behavior. Moreover, we prove that the dense-regime rate is minimax optimal for the empirical covariance error. Our numerical experiments validate these theoretical rates and demonstrate that appropriate subsampling preserves PCA accuracy while reducing computational cost.

期刊信息:International Conference on Machine Learning 2026

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v3,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v3 · 2026-11-17 00:26 · 最新观测版本

PCA of probability measures: Sparse and Dense sampling regimes

A common approach to perform PCA on probability measures is to embed them into a Hilbert space where standard functional PCA techniques apply. While convergence rates for estimating the embedding of a single measure from mm samples are well understood, the literature has not addressed the setting involving multiple measures. In this paper, we study PCA in a double asymptotic regime where nn probability measures are observed, each through mm samples. We derive convergence rates of the form n−1/2+m−αn^{-1/2} + m^{-α} for the empirical covariance operator and the PCA excess risk, where α>0α>0 depends on the chosen embedding. This characterizes the relationship between the number nn of measures and the number mm of samples per measure, revealing a sparse (small mm) to dense (large mm) transition in the convergence behavior. Moreover, we prove that the dense-regime rate is minimax optimal for the empirical covariance error. Our numerical experiments validate these theoretical rates and demonstrate that appropriate subsampling preserves PCA accuracy while reducing computational cost.

查看此版本解读 →查看此版本原文 ↗