Research map / Learning theory and algorithms / Matrix and tensor methods
Landscape analysis of an improved power method for tensor decomposition
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 |
|---|---|---|---|
| Use the SPM objective instead of the usual power-method objective | Symmetric tensor component recovery · Synthetic noiseless tensors | distance to nearest tensor component | Helped |
| Use the SPM objective instead of the usual power-method objective | Symmetric tensor component recovery · Synthetic noisy tensors | recovery error | Helped |
| Combine SPM with the modified deflation procedure | Complete symmetric tensor decomposition · Synthetic noisy tensors | component recovery error | Helped |
| Use noisy recovered components in successive deflation steps | SPM with modified deflation · Synthetic noisy tensors | error propagation | No clear effect |
Closest papers by meaning
- On the Optimization Landscape of Tensor Decompositions (NeurIPS 2017 · similarity 0.90)
- Tensor Decomposition via Joint Matrix Schur Decomposition (ICML 2016 · similarity 0.89)
- Fitting Low-Rank Tensors in Constant Time (NeurIPS 2017 · similarity 0.88)
- Tensor Ring Decomposition with Rank Minimization on Latent Space: An Efficient Approach for Tensor Completion (AAAI 2019 · similarity 0.88)
- More Efficient Sampling for Tensor Decomposition With Worst-Case Guarantees (ICML 2022 · similarity 0.88)
- Fast Tensor Completion via Approximate Richardson Iteration (ICML 2025 · similarity 0.87)
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.