Research map / Optimization / Implicit bias and generalization
Non-Convex SGD Learns Halfspaces with Adversarial Label Noise
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 a non-convex sigmoid surrogate instead of a convex surrogate | Halfspace learning with adversarial label noise · Gaussian marginals | misclassification error: \Omega(\mathrm{opt} \sqrt{\log(1/\mathrm{opt})}) vs. O(\mathrm{opt}) | Helped |
| Use a non-convex sigmoid objective instead of a convex loss | Halfspace learning with adversarial label noise · Log-concave marginals | misclassification error: \Omega(\mathrm{opt} \log(1/\mathrm{opt})) vs. O(\mathrm{opt}) | Helped |
| Use a non-convex sigmoid objective instead of a convex loss | Halfspace learning with adversarial label noise · s-heavy-tailed marginals, s>2 | misclassification error: \Omega(\mathrm{opt}^{1-1/s}) vs. O(\mathrm{opt}) | Helped |
Closest papers by meaning
- Learning General Halfspaces with Adversarial Label Noise via Online Gradient Descent (ICML 2022 · similarity 0.91)
- Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins (ICML 2021 · similarity 0.90)
- An Efficient Tester-Learner for Halfspaces (ICLR 2024 · similarity 0.90)
- Reliable Learning of Halfspaces under Gaussian Marginals (NeurIPS 2024 · similarity 0.88)
- A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise (NeurIPS 2024 · similarity 0.87)
- Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random (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.