Research map / Learning theory and algorithms / Kernels and regression theory
Margin-Based Generalization Lower Bounds for Boosted Classifiers
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 |
|---|---|---|---|
| Establish a lower bound that applies to every learning algorithm producing a voting classifier | Voting classifiers · Binary classification with empirical margin fraction at most \tau below margin \theta | generalization error lower bound: \tau + \Omega\left(\frac{\ln|\mathcal{H}|}{m \theta^2} + \sqrt{\tau \cdot \frac{\ln|\mathcal{H}|}{m \theta^2}}\right) | Mixed |
| Allow the poor-generalization voting classifier to be chosen as a function of the sample | Voting classifiers · Binary classification with empirical margin fraction at most \tau below margin \theta | generalization error lower bound: \tau + \Omega\left(\frac{\ln|\mathcal{H}|\ln m}{m \theta^2} + \sqrt{\tau \cdot \frac{\ln|\mathcal{H}|}{m \theta^2}}\righ | Mixed |
Closest papers by meaning
- Which Algorithms Have Tight Generalization Bounds? (NeurIPS 2025 · similarity 0.87)
- Fantastic Generalization Measures are Nowhere to be Found (ICLR 2024 · similarity 0.87)
- Revisiting Agnostic Boosting (NeurIPS 2025 · similarity 0.86)
- Certification-Enhanced Generalization Bounds (NeurIPS 2026 · similarity 0.86)
- Tight Generalization Bounds for Large-Margin Halfspaces (NeurIPS 2025 · similarity 0.86)
- Input Margins Can Predict Generalization Too (AAAI 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.