Research map / Learning theory and algorithms / Matrix and tensor methods
Sparse PCA via Covariance Thresholding
Yash Deshpande, Andrea Montanari
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 Covariance Thresholding instead of Diagonal Thresholding | sparse PCA support recovery · Synthetic sparse PCA, rank one | fraction of support recovered: n >~ s0^2 log p -> n >~ s0^2 | Improved |
| increase dimension p with s0 proportional to sqrt(n), Covariance Thresholding (ablation) | Covariance Thresholding · Synthetic sparse PCA, rank one | fraction of support recovered: increases monotonically with p for s0 <= 1.1 sqrt(n) | Improved |
| increase dimension p with s0 proportional to sqrt(n), Diagonal Thresholding (ablation) | Diagonal Thresholding · Synthetic sparse PCA, rank one | fraction of support recovered | Hurt |
| use data-driven Covariance Thresholding instead of Diagonal Thresholding at small n | wavelet-sparse signals (Three Peak, box), p=4096 · Three Peak and block-constant signals, beta=1.4 | signal reconstruction (visual) | Improved |
Closest papers by meaning
- Fast and Provable Algorithms for Sparse PCA with Improved Sample Complexity (ICML 2025 · similarity 0.94)
- A Kernel Random Matrix-Based Approach for Sparse PCA (ICLR 2019 · similarity 0.93)
- Combinatorial Sparse PCA Beyond the Spiked Identity Model (ICML 2026 · similarity 0.93)
- Efficient Sparse PCA via Block-Diagonalization (ICLR 2025 · similarity 0.92)
- The Complexity of Sparse Tensor PCA (NeurIPS 2021 · similarity 0.91)
- Oja's Algorithm for Streaming Sparse PCA (NeurIPS 2024 · similarity 0.90)
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.
