Research map / Learning theory and algorithms / Sample complexity
Sample and Computationally Efficient Learning Algorithms under S-Concave Distributions
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 |
|---|---|---|---|
| Extend margin-based active learning from log-concave to isotropic s-concave distributions | Halfspace learning with realizable labels · Isotropic s-concave distributions | label complexity as a function of 1/ε | Helped |
| Extend margin-based active learning from log-concave to isotropic s-concave distributions | Halfspace learning with adversarial label noise · Isotropic s-concave distributions | label complexity as a function of 1/ε | Helped |
| Use the derived disagreement coefficient for s-concave distributions | Disagreement-based active learning · Isotropic s-concave distributions | disagreement coefficient | Helped |
| Extend Baum's algorithm analysis from symmetric and log-concave distributions to s-concave distributions | Learning intersections of halfspaces · Isotropic s-concave distributions | label complexity | Helped |
Closest papers by meaning
- Non-Convex SGD Learns Halfspaces with Adversarial Label Noise (NeurIPS 2020 · similarity 0.87)
- Tester-Learners for Halfspaces: Universal Algorithms (NeurIPS 2023 · similarity 0.87)
- Online sampling from log-concave distributions (NeurIPS 2019 · similarity 0.86)
- The Sample Complexity of Gradient Descent in Stochastic Convex Optimization (NeurIPS 2024 · similarity 0.86)
- Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing (ICML 2024 · similarity 0.86)
- A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise (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.