Research map / Optimization / Nonconvex and smooth optimization
LazySVD: Even Faster SVD Decomposition Yet Without Agonizing Pain
Zeyuan Allen-Zhu, Yuanzhi Li
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 repeated single-vector 1-SVD instead of a block method | k-SVD · SNAP/amazon0302, SNAP/email-enron, news20, RCV1 | relative error versus running time | Improved |
| Use repeated single-vector 1-SVD instead of the block power method | k-SVD · SNAP/amazon0302, SNAP/email-enron, news20, RCV1 | relative error versus running time | Improved |
| Use unstable three-term recurrence for block Krylov | Block Krylov · selected experiments | performance at small T | Mixed |
| Use alternating minimization in the NNZ algorithm | NNZ k-SVD · k-SVD, NNZ | running time dependence on ε: 1/ε2 | Hurt |
| Subsample the matrix before applying LazySVD | LazySVD · k-SVD, NNZ | running time dependence on ε: 1/ε2 | Improved |
Closest papers by meaning
- Fast Stochastic Algorithms for SVD and PCA: Convergence Properties and Convexity (ICML 2016 · similarity 0.85)
- Fast Updating Truncated SVD for Representation Learning with Sparse Matrices (ICLR 2024 · similarity 0.83)
- Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares (ICML 2024 · similarity 0.82)
- Faster Algorithms for Structured Linear and Kernel Support Vector Machines (ICLR 2025 · similarity 0.82)
- Improved Algorithms for Kernel Matrix-Vector Multiplication Under Sparsity Assumptions (ICLR 2025 · similarity 0.82)
- The Structural Complexity of Matrix-Vector Multiplication (NeurIPS 2025 · similarity 0.82)
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.
