Research map / Learning theory and algorithms / Matrix and tensor methods
A sharp NMF result with applications in network modeling
Jiashun Jin
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 |
|---|---|---|---|
| Check condition (4.16) on the estimated Omega for UKFaculty (n=81, K=3) | Theorem 2.4 sufficient condition · UKFaculty network | max of estimated a_i vs threshold 1/(K-1) | Improved |
| Rotate estimated Y with the given 3x3 orthogonal Q to test non-negativity of Z | UKFaculty estimated Omega · UKFaculty network | smallest entry of each row of Z-hat | Improved |
| Apply Theorem 2.2 for K=2 to weblog and karate networks | DCMM rewrite of rank-2 model · Weblog (n=1,222, K=2) and karate | NMF solvability | Improved |
Closest papers by meaning
- On Mixed Memberships and Symmetric Nonnegative Matrix Factorizations (ICML 2017 · similarity 0.85)
- Characterizing the Loss Landscape in Non-Negative Matrix Factorization (AAAI 2021 · similarity 0.84)
- Regularized spectral methods for clustering signed networks (JMLR 2021 · similarity 0.84)
- Fitting Networks with a Cancellation Trick (ICLR 2025 · similarity 0.84)
- Non-negative Matrix Factorization under Heavy Noise (ICML 2016 · similarity 0.83)
- Statistically Optimal $K$-means Clustering via Nonnegative Low-rank Semidefinite Programming (ICLR 2024 · 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.
