AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

PCA Initialization for Approximate Message Passing in Rotationally Invariant Models

Marco Mondelli, Ramji Venkataramanan

NeurIPS 2021 · Learning theory and algorithms › Matrix and tensor methods · approach: Sparse and robust PCA · 13 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
use rotationally invariant PCA+AMP instead of the Gaussian-noise PCA+AMP (ablation)AMP with PCA initialization · simulated rank-1 estimation, free-cumulant noisenormalized squared correlation with signalImproved
run PCA+AMP instead of PCA alone under Marchenko-Pastur noisePCA estimator · square model, Marchenko-Pastur noisenormalized squared correlation with signalImproved
run PCA+AMP instead of PCA alone under uniform noisePCA estimator · uniform-spectrum noise, square and rectangularnormalized squared correlation with signalMixed
run PCA+AMP instead of PCA for right singular vector with Gaussian priorPCA estimator · rectangular model, right singular vectornormalized squared correlation with signalNo clear effect
compare AMP iterates against state evolution predictionsPCA+AMP · settings (a)-(d), 100 trialsagreement with state evolutionImproved

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