← 研踪 PaperTrailarXiv: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
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 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 probability measures are observed, each through samples. We derive convergence rates of the form for the empirical covariance operator and the PCA excess risk, where depends on the chosen embedding. This characterizes the relationship between the number of measures and the number of samples per measure, revealing a sparse (small ) to dense (large ) 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
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 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 probability measures are observed, each through samples. We derive convergence rates of the form for the empirical covariance operator and the PCA excess risk, where depends on the chosen embedding. This characterizes the relationship between the number of measures and the number of samples per measure, revealing a sparse (small ) to dense (large ) 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 ↗