Research map / Learning theory and algorithms / Matrix and tensor methods
Efficient Stochastic Optimization for Low-Rank Distance Metric Learning
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 incremental-SVD SGD with low-rank factorized iterates instead of GD, SGD, SGD-Batch, FW, SGD-One | Low-rank DML with nuclear norm · Gisette, Dexter objective vs. running time | convergence speed | Helped |
| use incremental-SVD SGD with factorized low-rank iterates | Low-rank DML with nuclear norm · News20 (d=62061) | memory feasibility | Helped |
| choose a suitable regularization lambda (e.g. 0.1 on Dexter) (ablation) | SGD-IncSVD · Dexter (d=20000) | rank of W_t: rank around 100 vs dimensionality 20000 | Helped |
Closest papers by meaning
- Learning Low-Dimensional Metrics (NeurIPS 2017 · similarity 0.88)
- Orthogonality-Promoting Distance Metric Learning: Convex Relaxation and Theoretical Analysis (ICML 2018 · similarity 0.88)
- Unsupervised Metric Learning with Synthetic Examples (AAAI 2020 · similarity 0.88)
- Large-Scale Distance Metric Learning With Uncertainty (CVPR 2018 · similarity 0.87)
- Distance Metric Learning with Joint Representation Diversification (ICML 2020 · similarity 0.87)
- Learning Distances from Data with Normalizing Flows and Score Matching (ICML 2025 · 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.