Research map / Learning theory and algorithms / Sample complexity
Revisiting Perceptron: Efficient and Label-Optimal Learning of Halfspaces
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 |
|---|---|---|---|
| Use AP instead of the prior bounded-noise algorithm in the comparison table | Active halfspace learning · Uniform unit sphere, bounded noise | label complexity | Helped |
| Use AP instead of prior active algorithms with unspecified-degree polynomial time | Active halfspace learning · Uniform unit sphere, adversarial noise | running time | Helped |
| Select examples from a positive-margin band [b/2,b] rather than querying only near-zero-margin examples | Modified Perceptron update · Uniform unit sphere, bounded and adversarial noise | angle to target halfspace | Helped |
| Convert AP to passive learning PP by rejection-sampling labeled examples from the data distribution | Halfspace learning · Uniform unit sphere, bounded noise | sample complexity | Helped |
Closest papers by meaning
- Active Learning of General Halfspaces: Label Queries vs Membership Queries (NeurIPS 2024 · similarity 0.91)
- An Efficient Tester-Learner for Halfspaces (ICLR 2024 · similarity 0.91)
- Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random (NeurIPS 2024 · similarity 0.89)
- A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise (NeurIPS 2024 · similarity 0.89)
- Replicable Learning of Large-Margin Halfspaces (ICML 2024 · similarity 0.87)
- Reliable Learning of Halfspaces under Gaussian Marginals (NeurIPS 2024 · similarity 0.87)
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.