Research map / Learning theory and algorithms / Matrix and tensor methods
On Approximation Guarantees for Greedy Low Rank Optimization
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 |
|---|---|---|---|
| Use greedy binomial PCA instead of SVD | Word embeddings from normalized counts · W353 | word similarity correlation: 0.226 -> 0.202 | Hurt |
| Use greedy binomial PCA instead of SVD | Word embeddings from normalized counts · MEN | word similarity correlation: 0.233 -> 0.198 | Hurt |
| Use greedy binomial PCA instead of PPMI | Word embeddings from normalized counts · MSR | analogy accuracy: 0.210 -> 0.176 | Hurt |
| Use greedy binomial PCA instead of PPMI | Word embeddings from normalized counts · Google | analogy accuracy: 0.130 -> 0.102 | Hurt |
| Use greedy binomial PCA instead of SGNS | Word embeddings from normalized counts · MEN | word similarity correlation: 0.020 -> 0.198 | Helped |
| Use greedy binomial PCA instead of SGNS | Word embeddings from normalized counts · MSR | analogy accuracy: 0.052 -> 0.176 | Helped |
| Use greedy binomial PCA instead of SGNS | Word embeddings from normalized counts · Google | analogy accuracy: 0.002 -> 0.102 | Helped |
Closest papers by meaning
- Local Search Algorithms for Rank-Constrained Convex Optimization (ICLR 2021 · similarity 0.89)
- Additive Error Guarantees for Weighted Low Rank Approximation (ICML 2021 · similarity 0.89)
- Efficient Low-Rank Matrix Estimation, Experimental Design, and Arm-Set-Dependent Low-Rank Bandits (ICML 2024 · similarity 0.88)
- Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · similarity 0.88)
- Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery (ICML 2025 · similarity 0.87)
- Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery (ICML 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.