Research map / Learning theory and algorithms / Matrix and tensor methods
Sharp analysis of power iteration for tensor PCA
Yuchen Wu, Kangjie Zhou
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 dimension n with lambda_n=n^((k-1)/2) | tensor power iteration with random init · Tensor PCA simulation, k=3 | gamma threshold for near-probability-one convergence | Improved |
| vary input dimension n | tensor power iteration · Tensor PCA, lambda_n=n^((k-1)/2) | iterations to convergence | No clear effect |
| add the proposed stopping rule T_stop | tensor power iteration · Tensor PCA, various (n,k), 5 tensors each | stopping time and estimation accuracy | Improved |
| alter the stopping threshold away from 1/2 (ablation) | T_stop stopping rule · Tensor PCA appendix experiments | stopping performance | No clear effect |
Closest papers by meaning
- Power Iteration for Tensor PCA (JMLR 2022 · similarity 0.93)
- The Complexity of Sparse Tensor PCA (NeurIPS 2021 · similarity 0.90)
- Sharp Recovery Thresholds of Tensor PCA Spectral Algorithms (NeurIPS 2023 · similarity 0.90)
- Analyzing Tensor Power Method Dynamics in Overcomplete Regime (JMLR 2017 · similarity 0.89)
- Tensor Decomposition via Simultaneous Power Iteration (ICML 2017 · similarity 0.88)
- Spectral Phase Transition and Optimal PCA in Block-Structured Spiked Models (ICML 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.
