Research map / Learning theory and algorithms / Matrix and tensor methods
A Fast Scale-Invariant Algorithm for Non-negative Least Squares with Non-negative Data
Jelena Diakonikolas, Chenghui Li, Swati Padmanabhan, Chaobing Song
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 SI-NNLS+ instead of FISTA and OA+DS | NNLS · real-sim | number of data passes | Improved |
| Add adaptive restart to SI-NNLS+ | SI-NNLS+ · real-sim | convergence to high accuracy | Improved |
| Use block size 1 instead of 10 | SI-NNLS+ with restart · real-sim | convergence | Improved |
| Use SI-NNLS+ with restart bs=1 instead of FISTA/OA+DS | NNLS · real-sim | runtime | Improved |
| Use SI-NNLS+ instead of FISTA and OA+DS | NNLS · news20 | number of data passes | Improved |
| Use block size 1 instead of 10 | SI-NNLS+ · news20 | runtime | Hurt |
| Use block size 10 with SI-NNLS+ | SI-NNLS+ · news20 | runtime | Improved |
| Use SI-NNLS+ instead of FISTA and OA+DS | NNLS · E2006train | function value reduction | Improved |
Closest papers by meaning
- Inexact Newton-type Methods for Optimisation with Nonnegativity Constraints (ICML 2024 · similarity 0.87)
- Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations (ICML 2017 · similarity 0.87)
- A Progressive Hierarchical Alternating Least Squares Method for Symmetric Nonnegative Matrix Factorization (TPAMI 2022 · similarity 0.86)
- Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression (JMLR 2017 · similarity 0.85)
- Non-negative Matrix Factorization under Heavy Noise (ICML 2016 · similarity 0.85)
- Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates (NeurIPS 2016 · 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.
