Research map / Learning theory and algorithms / Matrix and tensor methods
A Sharp Blockwise Tensor Perturbation Bound for Orthogonal Iteration
Yuetian Luo, Garvesh Raskutti, Ming Yuan, Anru R. Zhang
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 HOOI instead of the noisy tensor itself for reconstruction | HOOI · Simulated tensor reconstruction | Hilbert-Schmidt reconstruction error | Improved |
| increase dimension p and noise level sigma | HOOI · Simulated tensor reconstruction | RMSE | Hurt |
| use HOOI instead of T-HOSVD and ST-HOSVD | tensor denoising · Simulated tensor denoising (p=100, r=5) | reconstruction and subspace error | Improved |
| run only one HOOI iteration (O-HOOI) instead of full HOOI (ablation) | HOOI · Simulated tensor denoising (p=100, r=5) | reconstruction and subspace error | Mixed |
| use HOOI-based clustering instead of T-HOSVD, ST-HOSVD, O-HOOI based spectral clustering | tensor co-clustering · Simulated co-clustering (r=5) | misclassification error rate | Improved |
| increase signal strength | HOOI co-clustering · Simulated co-clustering | misclassification error rate | Improved |
Closest papers by meaning
- The Sup-norm Perturbation of HOSVD and Low Rank Tensor Denoising (JMLR 2019 · similarity 0.90)
- A Random Matrix Approach to Low-Multilinear-Rank Tensor Approximation (JMLR 2025 · similarity 0.90)
- Robust High-Order Tensor Compressive Sensing Based on M-Estimators (AAAI 2026 · similarity 0.87)
- Perturbation Bounds for Low-Rank Inverse Approximations under Noise (NeurIPS 2025 · similarity 0.86)
- Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy (NeurIPS 2025 · similarity 0.85)
- Towards Multi-Mode Outlier Robust Tensor Ring Decomposition (AAAI 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.
