Research map / Learning theory and algorithms / Sample complexity
Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Evolvability
Sitan Chen, Frederic Koehler, Ankur Moitra, Morris Yau
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 FILTERTRON instead of logistic regression under Massart noise | halfspace classifier · UCI Adult, high-income target group | accuracy on high-income target group | Improved |
| use FILTERTRON instead of gradient descent on LeakyReLU loss | halfspace classifier · UCI Adult, high-income target group | accuracy on high-income target group | Improved |
| use FILTERTRON instead of random forest | classifier · UCI Adult, high-income target group | accuracy on high-income target group | No clear effect |
| use FILTERTRON instead of baselines | classifier · UCI Adult, entire test set | overall accuracy | No clear effect |
Closest papers by meaning
- Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random (NeurIPS 2024 · similarity 0.93)
- A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise (NeurIPS 2024 · similarity 0.90)
- An Efficient Tester-Learner for Halfspaces (ICLR 2024 · similarity 0.90)
- Reliable Learning of Halfspaces under Gaussian Marginals (NeurIPS 2024 · similarity 0.89)
- Active Learning of General Halfspaces: Label Queries vs Membership Queries (NeurIPS 2024 · similarity 0.88)
- Distribution-Specific Agnostic Conditional Classification With Halfspaces (ICLR 2025 · similarity 0.88)
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.
