Research map / Learning theory and algorithms / Matrix and tensor methods
Fast and Provable Nonconvex Tensor RPCA
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 |
|---|---|---|---|
| Replace full transformed t-SVD in low-rank projection with tangent-space projection (EAPT vs APT) | EAPT · Synthetic n=500, q=5, r=5, alpha=0.3 | clock time | Helped |
| Use DCT instead of FFT as the unitary transform in EAPT (ablation) | EAPT · HSI denoising (CAVE) | PSNR | Helped |
| Use multi-rank truncation (frequency-adaptive rank) rather than tubal rank | EAPT · HSI denoising (CAVE) | PSNR | Helped |
| Use EAPT (tangent-space efficient projection) instead of T-TRPCA on HSI denoising | EAPT-DCT · HSI denoising (CAVE, 6 images) | PSNR and time | Helped |
| Replace DFT-based t-SVD in HSI denoising with DCT-based run of the proposed method | EAPT on HSI · HSI denoising (toys) | time | No clear effect |
Closest papers by meaning
- Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization (CVPR 2016 · similarity 0.94)
- A Nonconvex Projection Method for Robust PCA (AAAI 2019 · similarity 0.91)
- Outlier-Robust Tensor PCA (CVPR 2017 · similarity 0.90)
- The Complexity of Sparse Tensor PCA (NeurIPS 2021 · similarity 0.88)
- Fast Guaranteed Robust Local-Smooth Principal Component Separation (AAAI 2026 · similarity 0.88)
- RES-PCA: A Scalable Approach to Recovering Low-Rank Matrices (CVPR 2019 · similarity 0.88)
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.