Research map / Learning theory and algorithms / Matrix and tensor methods
Quadratic Matrix Factorization With Applications to Manifold Learning
Zheng Zhai, Hengchao Chen, Qiang Sun
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 quadratic (curvature-aware) RQMF-E instead of Local PCA | manifold denoising · Synthetic sphere, K=16 | MSE: 0.0432 -> 0.0115 | Improved |
| use RQMF-E instead of Moving LS | manifold denoising · Synthetic sphere, K=28 | MSE: 0.2642 -> 0.0156 | Improved |
| use kernel weights (RQMF-K) instead of equal weights (RQMF-E) at small K | RQMF · Synthetic sphere, K=7 | MSE: 0.0243 -> 0.0188 | Improved |
| use RQMF-K instead of RQMF-E at larger K | RQMF · Synthetic sphere, K=16 | MSE: 0.0115 -> 0.0148 | Hurt |
| use larger delta (smaller lambda) at large K (ablation) | RQMF-E · Synthetic sphere | MSE | Improved |
| use RQMF-E instead of Local-PCA | manifold denoising · Cryo-EM, K=48 | MSE: 1.7364 -> 1.3482 | Improved |
| use RQMF-K instead of RQMF-E | RQMF · Cryo-EM, K=48 | MSE: 1.3482 -> 2.0718 | Hurt |
| use RQMF-K instead of the original image | MNIST principal curve · MNIST image 3 | average |I*w|: 1.0306 -> 0.5168 | Improved |
| use RQMF-K instead of KDE | MNIST principal curve · MNIST image 3 | average |I*w|: 0.7574 -> 0.5168 | Improved |
Closest papers by meaning
- A Unified Framework for Structured Low-rank Matrix Learning (ICML 2018 · similarity 0.87)
- Structured Low-Rank Matrix Factorization: Global Optimality, Algorithms, and Applications (TPAMI 2019 · similarity 0.87)
- Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion (NeurIPS 2024 · similarity 0.86)
- Robust Manifold Matrix Factorization for Joint Clustering and Feature Extraction (AAAI 2017 · similarity 0.86)
- Fixed-Rank Supervised Metric Learning on Riemannian Manifold (AAAI 2016 · similarity 0.85)
- Supervised Matrix Factorization: Local Landscape Analysis and Applications (ICML 2024 · 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.
