Research map / Learning theory and algorithms / Matrix and tensor methods
Additive Error Guarantees for Weighted Low Rank Approximation
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 |
|---|---|---|---|
| greedy rank-1 weighted LRA (wlra-iter) vs unweighted SVD baseline | weighted low rank approximation · synthetic semirandom weights (W3) | scaled weighted error | Helped |
| greedy rank-1 weighted LRA vs SVD on uniform random weights (W1) | weighted low rank approximation · synthetic random weights (W1) | scaled weighted error | No clear effect |
| Assumption on ||L||_F^2 <= Lambda ||A||_F^2 with additive error bound, versus optimal cost (Theorem 1 guarantee) | greedy weighted L2 algorithm · theory | Cost(L') bound | Helped |
| Extend greedy algorithm to entrywise l_p error with p>2 (Theorem 2) | weighted low rank approximation with l_p error · theory | Cost_p bound | Helped |
Closest papers by meaning
- Regularized Weighted Low Rank Approximation (NeurIPS 2019 · similarity 0.92)
- Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation (ICLR 2025 · similarity 0.90)
- Reweighted Solutions for Weighted Low Rank Approximation (ICML 2024 · similarity 0.90)
- Entrywise error bounds for low-rank approximations of kernel matrices (NeurIPS 2024 · similarity 0.87)
- On Socially Fair Low-Rank Approximation and Column Subset Selection (NeurIPS 2024 · similarity 0.87)
- Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time (ICLR 2024 · 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.