Research map / Learning theory and algorithms / Kernels and regression theory
The Teaching Dimension of Linear Learners
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 |
|---|---|---|---|
| add a bias term (inhomogeneous) | ridge regression · exact parameter | teaching dimension: 1 -> 2 | Hurt |
| add a bias term (inhomogeneous) | SVM · decision boundary | teaching dimension: 1 -> 2 | Hurt |
| add a bias term (inhomogeneous) | logistic regression · decision boundary | teaching dimension: 1 -> 2 | Hurt |
| teach decision boundary instead of exact parameter | SVM homogeneous · teaching goal | teaching dimension | Helped |
| teach decision boundary instead of exact parameter | logistic regression homogeneous · teaching goal | teaching dimension | Helped |
| increase regularization lambda or target norm | SVM and logistic regression · exact parameter | teaching dimension | Hurt |
| vary feature dimension d | SVM inhomogeneous · decision boundary | teaching dimension | No clear effect |
Closest papers by meaning
- The Teaching Dimension of Regularized Kernel Learners (ICML 2022 · similarity 0.90)
- Gradient-Based Algorithms for Machine Teaching (CVPR 2021 · similarity 0.86)
- How a Student becomes a Teacher: learning and forgetting through Spectral methods (NeurIPS 2023 · similarity 0.86)
- Piecewise Constant and Linear Regression Trees: An Optimal Dynamic Programming Approach (ICML 2024 · similarity 0.83)
- Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate (NeurIPS 2024 · similarity 0.83)
- Toward Student-oriented Teacher Network Training for Knowledge Distillation (ICLR 2024 · similarity 0.83)
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.