Research map / Learning theory and algorithms / Prediction and decision losses
Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space 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 |
|---|---|---|---|
| Use adaptive teaching with local, state-dependent learner preferences | 2-Rec teaching · 2-Rec | teaching complexity | Helped |
| Use adaptive teaching instead of non-adaptive teaching | Lattice teaching with local preferences · Lattice | teaching complexity: at most 3(b-a) vs. at least 4(b-a) | Helped |
| Use adaptive teaching instead of non-adaptive teaching | 2-Rec teaching with local preferences · 2-Rec | teaching complexity: \Theta(\log|r_{2}|) vs. \Theta(|r_{2}|) | Helped |
| Use an adaptive teacher rather than a non-adaptive teacher | State-independent preference learners · Version space learners | teaching complexity | No clear effect |
| Use Ada-R rather than SC | Simulated noisy learners · 2-Rec, noisy setting | teaching complexity | Helped |
| Use Ada-R rather than SC | Human learners · 2-Rec teaching scenarios | number of teaching examples | Helped |
| Use SC rather than Ada-R | Human learners with targets in H² · 2-Rec, H¹→H² and H²→H² | number of teaching examples | No clear effect |
| Use local preferences that depend on the learner's current hypothesis | Version space teaching · 2-Rec and Lattice | adaptivity gain | Helped |
| Require ties among the learner's local preferences | Adaptive teaching · State-dependent preference models | adaptivity gain | Helped |
Closest papers by meaning
- Teaching with Limited Information on the Learner’s Behaviour (ICML 2020 · similarity 0.87)
- Preference-Based Batch and Sequential Teaching: Towards a Unified View of Models (NeurIPS 2019 · similarity 0.87)
- Iterative Classroom Teaching (AAAI 2019 · similarity 0.87)
- Machine Teaching of Active Sequential Learners (NeurIPS 2019 · similarity 0.86)
- B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners (ICLR 2025 · similarity 0.83)
- Improving Environment Novelty Quantification for Effective Unsupervised Environment Design (NeurIPS 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.