Research map / Learning theory and algorithms / Matrix and tensor methods
PCA Initialization for Approximate Message Passing in Rotationally Invariant Models
Marco Mondelli, Ramji Venkataramanan
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use rotationally invariant PCA+AMP instead of the Gaussian-noise PCA+AMP (ablation) | AMP with PCA initialization · simulated rank-1 estimation, free-cumulant noise | normalized squared correlation with signal | Improved |
| run PCA+AMP instead of PCA alone under Marchenko-Pastur noise | PCA estimator · square model, Marchenko-Pastur noise | normalized squared correlation with signal | Improved |
| run PCA+AMP instead of PCA alone under uniform noise | PCA estimator · uniform-spectrum noise, square and rectangular | normalized squared correlation with signal | Mixed |
| run PCA+AMP instead of PCA for right singular vector with Gaussian prior | PCA estimator · rectangular model, right singular vector | normalized squared correlation with signal | No clear effect |
| compare AMP iterates against state evolution predictions | PCA+AMP · settings (a)-(d), 100 trials | agreement with state evolution | Improved |
Closest papers by meaning
- Estimation in Rotationally Invariant Generalized Linear Models via Approximate Message Passing (ICML 2022 · similarity 0.89)
- The price of ignorance: how much does it cost to forget noise structure in low-rank matrix estimation? (NeurIPS 2022 · similarity 0.85)
- Fast and Provable Algorithms for Sparse PCA with Improved Sample Complexity (ICML 2025 · similarity 0.83)
- Spectral Phase Transition and Optimal PCA in Block-Structured Spiked Models (ICML 2024 · similarity 0.83)
- Low Precision Streaming PCA (NeurIPS 2025 · similarity 0.83)
- Oja's Algorithm for Streaming Sparse PCA (NeurIPS 2024 · similarity 0.82)
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.
