Research map / Learning theory and algorithms / Sample complexity
Learning Low-Dimensional Metrics
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 ℓ1,2 regularization instead of nuclear-norm regularization | Metric learning · Sparse low-rank metric simulation | relative excess risk | Helped |
| Use nuclear-norm regularization instead of ℓ1,2 regularization | Metric learning · Dense low-rank metric simulation | relative excess risk | Helped |
| Constrain the metric with nuclear-norm or ℓ1,2 regularization rather than only requiring it to be PSD | Metric learning · Sparse and dense low-rank metric simulations | relative excess risk | Helped |
| Use nuclear-norm regularization rather than ℓ1,2 regularization | Metric learning · Sparse and dense low-rank metric simulations | relative excess risk | Mixed |
Closest papers by meaning
- Dimensionality reduction: theoretical perspective on practical measures (NeurIPS 2019 · similarity 0.90)
- Unsupervised Metric Learning with Synthetic Examples (AAAI 2020 · similarity 0.90)
- Efficient Stochastic Optimization for Low-Rank Distance Metric Learning (AAAI 2017 · similarity 0.88)
- Joint Dimensionality Reduction and Metric Learning: A Geometric Take (ICML 2017 · similarity 0.88)
- Variational Metric Scaling for Metric-Based Meta-Learning (AAAI 2020 · similarity 0.88)
- Metric Space Magnitude for Evaluating the Diversity of Latent Representations (NeurIPS 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.