Research map / Optimization / Implicit bias and generalization
Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations
Yuanzhi Li, Yingyu Liang
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 AND instead of HALS or ANLS | NMF feature recovery · DIR and CTM | total correlation error | Improved |
| Use AND instead of HALS or ANLS | NMF feature recovery · NEG | total correlation error | Improved |
| Use a decreasing threshold instead of a constant threshold (ablation) | AND · DIR and CTM | total correlation error | Improved |
| Add noise to the observations (ablation) | AND · NOISE | total correlation error | Mixed |
Closest papers by meaning
- Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates (NeurIPS 2016 · similarity 0.91)
- Convergence of Alternating Gradient Descent for Matrix Factorization (NeurIPS 2023 · similarity 0.91)
- Characterizing the Loss Landscape in Non-Negative Matrix Factorization (AAAI 2021 · similarity 0.89)
- Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks (NeurIPS 2024 · similarity 0.87)
- In-depth Analysis of Low-rank Matrix Factorisation in a Federated Setting (AAAI 2025 · similarity 0.87)
- Efficient Alternating Minimization with Applications to Weighted Low Rank Approximation (ICLR 2025 · similarity 0.86)
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.
