Research map / Learning theory and algorithms / Sample complexity
Near-Optimal Cryptographic Hardness of Agnostically Learning Halfspaces and ReLU Regression under Gaussian Marginals
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 |
|---|---|---|---|
| Reduce LWE to agnostic halfspace learning using a small-norm continuous-LWE secret | Gaussian-marginal agnostic halfspace learning · Gaussian marginals | running time lower bound: n^{Ω(1/(ε√log n)^α)} | Helped |
| Reduce LWE to ReLU regression by converting the periodic hidden-direction signal into a ReLU correlation | Gaussian-marginal ReLU regression · Gaussian marginals | running time lower bound: n^{O(1/(ε log^2 n)^α)} | Helped |
| Remove the √log m factor from the small-secret-norm reduction (ablation) | LWE-to-Gaussian-halfspace hardness reduction · Gaussian-marginal agnostic halfspace learning | running time lower bound: n^{Ω(1/(ε√log n)^{0.99})} -> n^{Ω(1/(ε√log n)^{1.99})} | Helped |
Closest papers by meaning
- Reliable Learning of Halfspaces under Gaussian Marginals (NeurIPS 2024 · similarity 0.89)
- Smoothed Agnostic Learning of Halfspaces over the Hypercube (NeurIPS 2025 · similarity 0.87)
- Cryptographic Hardness of Score Estimation (NeurIPS 2024 · similarity 0.86)
- Testably Learning Polynomial Threshold Functions (NeurIPS 2024 · similarity 0.85)
- An Efficient Tester-Learner for Halfspaces (ICLR 2024 · similarity 0.85)
- 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.