Research map / Learning theory and algorithms / Prediction and decision losses
Teaching to Learn: Sequential Teaching of Learners with Internal States
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 |
|---|---|---|---|
| Teach the learner about collinearity so its internal state becomes enlightened | Simulated human user in interactive variable selection · 10 test datasets, same collinearity as teaching data | terminal cost: 12.34 (stdev 0.29) -> 2.18 (stdev 0.44) | Helped |
| Include an estimate of independent-learning performance on future tasks in the teaching cost | Teaching to Learn (TtL) · Interactive variable selection | cumulative cost | Helped |
| Choose and order tasks to guide the online meta-learner toward a good initialization | Online meta-learner using follow-the-meta-leader · Sine-function regression tasks | 2-shot prediction loss | Helped |
| Use a manipulative teacher that never tutors instead of tutoring the learner | Simulated human user in interactive variable selection · Future independent learning on related datasets | terminal cost: 2.18 (stdev 0.44) -> 12.34 (stdev 0.29) | Hurt |
Closest papers by meaning
- Machine Teaching of Active Sequential Learners (NeurIPS 2019 · similarity 0.89)
- Iterative Classroom Teaching (AAAI 2019 · similarity 0.88)
- Teaching with Limited Information on the Learner’s Behaviour (ICML 2020 · similarity 0.88)
- Nonparametric Teaching for Multiple Learners (NeurIPS 2023 · similarity 0.86)
- Learning to Learn with Contrastive Meta-Objective (NeurIPS 2025 · similarity 0.84)
- Can Students Beyond the Teacher? Distilling Knowledge from Teacher’s Bias (AAAI 2025 · similarity 0.84)
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.