Research map / Learning theory and algorithms / Matrix and tensor methods
Power Iteration for Tensor PCA
Jiaoyang Huang, Daniel Z. Huang, Qing Yang, Guang Cheng
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 |
|---|---|---|---|
| increase signal strength from beta=5 to beta=10 | rank-one tensor power iteration · Rank-one spiked tensor (n=600, k=3) | Gaussian fit of normalized estimators: beta=5 -> beta=10 | Improved |
| use informative initialization (v+w)/norm instead of random | tensor power iteration · Rank-one spiked tensor (n=600, k=3) | asymptotic Gaussianity at small beta: beta=5, beta=10 | Improved |
| increase signal strength beta above n^((k-2)/2) with random initialization | tensor power iteration · Rank-one spiked tensor (k=3) | signal recovery | Improved |
| increase informative initialization strength beta<u0,v> with fixed beta=3 | tensor power iteration · Rank-one spiked tensor (k=3) | signal recovery: beta<u0,v> in (0,2] | Improved |
| increase dimension n from 50 to 800 | tensor power iteration · Rank-2 spiked tensor, k=3 | 95% CI coverage for beta1: 0.9136 -> 0.9551 | Mixed |
| increase dimension n from 50 to 800 | tensor power iteration · Rank-2 spiked tensor, k=3 | fraction p1 converging to beta1: 0.405 -> 0.401 | No clear effect |
Closest papers by meaning
- Sharp analysis of power iteration for tensor PCA (JMLR 2024 · similarity 0.93)
- The Complexity of Sparse Tensor PCA (NeurIPS 2021 · similarity 0.88)
- Analyzing Tensor Power Method Dynamics in Overcomplete Regime (JMLR 2017 · similarity 0.88)
- Sharp Recovery Thresholds of Tensor PCA Spectral Algorithms (NeurIPS 2023 · similarity 0.87)
- The spiked matrix model with generative priors (NeurIPS 2019 · similarity 0.86)
- Fast and Provable Algorithms for Sparse PCA with Improved Sample Complexity (ICML 2025 · similarity 0.84)
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.
