Research map / Learning theory and algorithms / Matrix and tensor methods
Principal Component Projection and Regression in Nearly Linear Time through Asymmetric SVRG
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 |
|---|---|---|---|
| Use rational sign approximation and asymmetric SVRG instead of polynomial approximation and ridge-regression subproblems | PCP · PCP | runtime | Helped |
| Use rational sign approximation and asymmetric SVRG instead of polynomial approximation and ridge-regression subproblems | PCR · PCR | runtime | Helped |
| Solve the asymmetric system directly rather than applying SVRG to its squared counterpart | Asymmetric SVRG · Non-PSD linear systems | runtime | Helped |
| Use asymmetric SVRG rather than AGD on the squared counterpart | Asymmetric SVRG · Non-PSD linear systems | runtime | Helped |
| Combine rational Lanczos search with ISPCP (ablation) | ISPCP · PCP, low-accuracy regime | vector-vector products | Helped |
| Combine rational Lanczos search with ISPCP (ablation) | ISPCP · PCP, high-accuracy regime | stability | Mixed |
| Use ISPCP, rlanczos, or slanczos instead of polynomial, Chebyshev, or Lanczos baselines | PCP algorithms · Synthetic eigenvalue distributions | vector-vector products | Helped |
| Apply the PCP methods to a no-eigengap eigenvalue distribution | PCP algorithms · Synthetic No-Eigengap-Skewed Case | precision | Hurt |
Closest papers by meaning
- Efficient Sparse PCA via Block-Diagonalization (ICLR 2025 · similarity 0.83)
- No Double Descent in Principal Component Regression: A High-Dimensional Analysis (ICML 2024 · similarity 0.83)
- Invariant subspaces and PCA in nearly matrix multiplication time (NeurIPS 2024 · similarity 0.83)
- Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nyström method (ICML 2024 · similarity 0.83)
- Generalization Bound and Learning Methods for Data-Driven Projections in Linear Programming (NeurIPS 2024 · similarity 0.83)
- Oja's Algorithm for Streaming Sparse PCA (NeurIPS 2024 · similarity 0.83)
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.