Research map / Learning theory and algorithms / Prediction and decision losses
Provable Gaussian Embedding with One Observation
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 |
|---|---|---|---|
| Ignore the conditional covariance matrices rather than use known covariances | Gaussian embedding estimator · Gaussian embedding, p=1000 | relative Frobenius estimation error: 0.7142 -> 0.8184 | Hurt |
| Ignore the conditional covariance matrices rather than use known covariances | Gaussian embedding estimator · Gaussian embedding, p=2500 | relative Frobenius estimation error: 0.3990 -> 0.4432 | Hurt |
| Ignore the conditional covariance matrices rather than use known covariances | Gaussian embedding estimator · Gaussian embedding, p=5000 | relative Frobenius estimation error: 0.2908 -> 0.3210 | Hurt |
| Ignore the conditional covariance matrices rather than use known covariances | Gaussian embedding estimator · Gaussian embedding, p=8000 | relative Frobenius estimation error: 0.2288 -> 0.2472 | Hurt |
| Ignore the conditional covariance matrices rather than use known covariances | Gaussian embedding estimator · Gaussian embedding, p=15000 | relative Frobenius estimation error: 0.1649 -> 0.1723 | Hurt |
| Use non-convex optimization instead of convex relaxation | Gaussian embedding estimator · Chain, nearest-neighbor, and lattice structures | relative Frobenius estimation error | Mixed |
| Use non-convex optimization instead of convex relaxation | Gaussian embedding estimator · Chain, nearest-neighbor, and lattice structures | test loss | Helped |
| Increase the number of nodes | Convex and non-convex Gaussian embedding estimators · Chain, nearest-neighbor, and lattice structures | test loss | Helped |
Closest papers by meaning
- Exponential Family Embeddings (NeurIPS 2016 · similarity 0.87)
- Optimization Can Learn Johnson Lindenstrauss Embeddings (NeurIPS 2024 · similarity 0.85)
- Generalization Guarantees for Representation Learning via Data-Dependent Gaussian Mixture Priors (ICLR 2025 · similarity 0.84)
- Hyperbolic Embeddings of Supervised Models (NeurIPS 2024 · similarity 0.84)
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · similarity 0.84)
- When is an Embedding Model More Promising than Another? (NeurIPS 2024 · similarity 0.84)
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.