Research map / Label-efficient and robust learning / Recognition and long-tail
On the Power and Limits of Distance-Based Learning
Periklis Papakonstantinou, Jia Xu, Guang Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| learner given full description of two experts vs. only query access to experts | distance-based learning of low-distortion embeddings in edit spaces · theoretical lower bound, edit space X=Y={0,1}^{2n} | generalization error R(C) | No clear effect |
| adding polynomially many queries to the target concept and experts | learners in edit-space low-distortion embedding setting · theoretical lower bound, edit space | generalization error R(C) | No clear effect |
Closest papers by meaning
- Margin-Independent Online Multiclass Learning via Convex Geometry (NeurIPS 2021 · similarity 0.86)
- Margin-Based Active Learning of Classifiers (JMLR 2024 · similarity 0.86)
- Learning Low-Dimensional Metrics (NeurIPS 2017 · similarity 0.86)
- Fully Dynamic Embedding into $\ell_p$ Spaces (ICML 2025 · similarity 0.85)
- Conveyance: A Versatile Framework for Learning in Structured Class Spaces (NeurIPS 2026 · similarity 0.85)
- Hyperbolic Embeddings of Supervised Models (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.
