Research map / Learning theory and algorithms / Kernels and regression theory
Mentored Learning: Improving Generalization and Convergence of Student Learner
Xiaofeng Cao, Yaming Guo, Heng Tao Shen, Ivor W. Tsang, James T. Kwok
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 |
|---|---|---|---|
| guide hypothesis pruning with an approximately optimal teacher (ATML vs IWAL) | IWAL · six UCI datasets | candidate hypothesis set size | Improved |
| add self-improvement of teaching (new hypotheses by convex combination) (ablation) | ATML · six UCI datasets | generalization error of teaching hypothesis | Improved |
| use ATML instead of IWAL and IWAL-D | IWAL / IWAL-D · six UCI datasets (white-box) | test error rate | Improved |
| use teacher-learner disagreement for pruning (ATML) vs learner-only disagreement (IWAL-D) vs none (IWAL) | IWAL-D · six UCI datasets (white-box) | number of query labels | Improved |
| use ATML+ with pretrained CNN teacher instead of MVR, ME, Random | MVR / ME / Random · mnist 3 vs 5 (black-box CNN) | test accuracy | Improved |
Closest papers by meaning
- Teaching with Limited Information on the Learner’s Behaviour (ICML 2020 · similarity 0.88)
- Theoretical Analysis of Weak-to-Strong Generalization (NeurIPS 2024 · similarity 0.86)
- Theory of Curriculum Learning, with Convex Loss Functions (JMLR 2020 · similarity 0.86)
- On the Mechanisms of Weak-to-Strong Generalization: A Theoretical Perspective (NeurIPS 2025 · similarity 0.86)
- Toward Student-oriented Teacher Network Training for Knowledge Distillation (ICLR 2024 · similarity 0.85)
- Progressive distillation induces an implicit curriculum (ICLR 2025 · 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.
