AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

PCA of Probability Measures: Sparse and Dense Sampling Regimes

Erell Gachon, Jérémie Bigot, Elsa Cazelles

ICML 2026 · Learning theory and algorithms › Kernels and regression theory · approach: Kernel regression under shift · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase ambient dimension d from 2 to 50LOT embedding · Simulated Gaussian measurescovariance risk x100: 2.40 -> 235.64Hurt
increase ambient dimension d from 2 to 50KME embedding · Simulated Gaussian measurescovariance risk x100: 1.43 -> 12.64Hurt
increase ambient dimension d from 2 to 50SW embedding · Simulated Gaussian measurescovariance risk x100: 0.71 -> 0.52No clear effect
increase ambient dimension d from 2 to 50LOT embedding · Simulated Gaussian measuresPCA excess risk x100: 0.07 -> 0.93Hurt
increase ambient dimension d from 2 to 50SW embedding · Simulated Gaussian measuresPCA excess risk x100: 0.02 -> 0.02No clear effect
increase number of components q from 1 to 10SW embedding · Simulated Gaussian measuresPCA excess risk x100: 0.13 -> 7.91Hurt
increase number of components q from 1 to 10KME embedding · Simulated Gaussian measuresPCA excess risk x100: 16.23 -> 53.79Hurt
use SW instead of KME embedding at q=10PCA excess risk · Simulated Gaussian measuresPCA excess risk x100: 53.79 -> 7.91Improved
increase number of measures n from 10 to 1000 (dense regime)KME, LOT, SW · Simulated Gaussian measurescovariance risk: slope close to -1/2Improved
increase number of measures n from 10 to 1000 (dense regime)KME, LOT, SW · Simulated Gaussian measuresPCA excess risk: slope close to -1Improved
subsample 50 cells per measure instead of 2000PCA with KME, LOT, SW · HIPC flow cytometry (n=63)2D PCA representation stability: m=50 vs m=2000No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy