Research map / Learning theory and algorithms / Prediction and decision losses
Finite Sample Prediction and Recovery Bounds for Ordinal Embedding
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 rank-d projected gradient descent instead of gradient descent directly on the embedding | Ordinal embedding with logistic loss · Synthetic data | runtime: an order of magnitude faster | Helped |
| Debias the nuclear-norm PGD solution by refitting its top-d eigenvalues (ablation) | Nuclear Norm PGD · Synthetic data | embedding accuracy | Helped |
| Use rank-d PGD rather than nuclear-norm PGD without debiasing | Ordinal embedding with logistic loss · Synthetic data | embedding accuracy | Mixed |
| Optimize the embedding directly with gradient descent rather than optimize the Gram matrix with rank-d PGD | Ordinal embedding with logistic loss · Synthetic data | Gram matrix similarity | No clear effect |
Closest papers by meaning
- Scaling Up Ordinal Embedding: A Landmark Approach (ICML 2019 · similarity 0.93)
- Landmark Ordinal Embedding (NeurIPS 2019 · similarity 0.92)
- Embedding Dimension of Contrastive Learning and $k$-Nearest Neighbors (NeurIPS 2024 · similarity 0.86)
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · similarity 0.86)
- On the rankability of visual embeddings (NeurIPS 2025 · similarity 0.85)
- Optimization Can Learn Johnson Lindenstrauss Embeddings (NeurIPS 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.