Research map / Label-efficient and robust learning / Recognition and long-tail
Less but Better: Generalization Enhancement of Ordinal Embedding via Distributional Margin
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 |
|---|---|---|---|
| Optimize margin distribution rather than only the minimum margin | Ordinal embedding · Synthetic dataset, 200 training samples | generalization error (median): 0.468 -> 0.390 | Helped |
| Optimize margin distribution rather than only the minimum margin | Ordinal embedding · Synthetic dataset, 1000 training samples | generalization error (median): 0.441 -> 0.298 | Helped |
| Optimize margin distribution rather than only the minimum margin | Ordinal embedding · Synthetic dataset, 10000 training samples | generalization error (median): 0.257 -> 0.146 | Helped |
| Optimize margin distribution rather than only the minimum margin | Ordinal embedding · Music artists, 200 training samples | generalization error (median): 0.403 -> 0.385 | Helped |
| Optimize margin distribution rather than only the minimum margin | Ordinal embedding · Music artists, 1000 training samples | generalization error (median): 0.415 -> 0.291 | Helped |
| Optimize margin distribution rather than only the minimum margin | Ordinal embedding · Music artists, 5000 training samples | generalization error (median): 0.239 -> 0.227 | Helped |
| Use margin distribution optimization instead of maximizing only the minimum margin | Ordinal embedding · Synthetic dataset, few training samples | generalization ability | Helped |
| Maximize only the minimum margin rather than modeling the margin distribution | GNMDS-p ordinal embedding · Synthetic dataset, few training samples | generalization performance | Hurt |
Closest papers by meaning
- Finite Sample Prediction and Recovery Bounds for Ordinal Embedding (NeurIPS 2016 · similarity 0.91)
- Landmark Ordinal Embedding (NeurIPS 2019 · similarity 0.90)
- Scaling Up Ordinal Embedding: A Landmark Approach (ICML 2019 · similarity 0.90)
- On the rankability of visual embeddings (NeurIPS 2025 · similarity 0.85)
- On Statistical Learning Theory for Distributional Inputs (ICML 2024 · similarity 0.84)
- Learning to Embed Distributions via Maximum Kernel Entropy (NeurIPS 2024 · similarity 0.83)
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.