Research map / Learning theory and algorithms / Sample complexity
Supervised learning through the lens of compression
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 |
|---|---|---|---|
| move from standard sample compression to agnostic sample compression, for multiclass learning | sample compression schemes · multiclass categorization (theory, no experiments) | compression size | Helped |
| assume non-trivial compression exists, e.g. size m^0.99 | sample compression · multiclass categorization (theory) | compression size: m^0.99 -> roughly log m | Helped |
| assume uniform convergence property | multiclass classes · theory | compression size | Helped |
| move from zero/one loss to general loss functions | PAC versus agnostic PAC learnability · three-valued loss (theory) | equivalence of PAC and agnostic PAC | Hurt |
| use exact compression instead of approximate compression, for general losses | linear regression example · general loss (theory) | equivalence with learnability | Hurt |
Closest papers by meaning
- Representation Preserving Multiclass Agnostic to Realizable Reduction (ICML 2025 · similarity 0.89)
- Transductive Learning is Compact (NeurIPS 2024 · similarity 0.88)
- Does Compression Imply Generalization? A Minimum Description Length Perspective (NeurIPS 2026 · similarity 0.87)
- Agnostic Sample Compression Schemes for Regression (ICML 2024 · similarity 0.87)
- Surprises in Proper Positive-Only Learning (NeurIPS 2026 · similarity 0.85)
- Scale-Sensitive Shattering: Learnability and Evaluability at Optimal Scale (NeurIPS 2026 · 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.