Research map / Learning theory and algorithms / Matrix and tensor methods
Tensor Decomposition via Simultaneous Power Iteration
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 |
|---|---|---|---|
| Simultaneous tensor power method with a gap-preserving initialization (k vectors updated together with QR) instead of deflation one vector at a time | orthogonal symmetric order-3 tensor decomposition (batch) · batch setting, theoretical | iterations to reach error epsilon | Helped |
| Streaming algorithm using O(kd) memory instead of storing the full tensor or O(dk log k) memory | orthogonal symmetric order-3 tensor decomposition (streaming) · streaming setting, theoretical | memory and sample complexity | Helped |
| Whitening via a single matrix power iteration (QR of M Z) instead of full SVD or matrix power method to convergence | nonorthogonal symmetric tensor whitening · theoretical | convergence cost of whitening | Helped |
Closest papers by meaning
- Tensor Decomposition via Joint Matrix Schur Decomposition (ICML 2016 · similarity 0.88)
- Landscape analysis of an improved power method for tensor decomposition (NeurIPS 2021 · similarity 0.88)
- Fast Tensor Completion via Approximate Richardson Iteration (ICML 2025 · similarity 0.87)
- Streaming Coresets for Symmetric Tensor Factorization (ICML 2020 · similarity 0.87)
- Tensor Completion Made Practical (NeurIPS 2020 · similarity 0.86)
- Efficient Leverage Score Sampling for Tensor Train Decomposition (NeurIPS 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.