Research map / Learning theory and algorithms / Matrix and tensor methods
Principal Component Projection Without Principal Component Analysis
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Increase number of iterations of PC-PROJ (sharpening polynomial) on synthetic data | PC-PROJ · Synthetic data, gaps γ=.1, .02, .01 | projection error | Helped |
| Smaller spectral gap γ | PC-PROJ · Synthetic data | projection error | Hurt |
| Projection replaced by PCR via RIDGE-PCR iterations | RIDGE-PCR · MNIST regression | relative regression error | Helped |
| Projection with ridge-regression-based sharpening, 20 iterations | PC-PROJ · MNIST regression | relative projection error: 0.01 relative error at 20 iterations | Helped |
Closest papers by meaning
- Principal Component Projection and Regression in Nearly Linear Time through Asymmetric SVRG (NeurIPS 2019 · similarity 0.90)
- Efficient Sparse PCA via Block-Diagonalization (ICLR 2025 · similarity 0.88)
- Faster Principal Component Regression and Stable Matrix Chebyshev Approximation (ICML 2017 · similarity 0.88)
- Local Linear Convergence of Gradient Methods for Subspace Optimization via Strict Complementarity (NeurIPS 2022 · similarity 0.87)
- Additive Component Analysis (CVPR 2017 · similarity 0.86)
- Oja's Algorithm for Streaming Sparse PCA (NeurIPS 2024 · similarity 0.85)
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.