mlsanityData to 14 Oct 2026

The Teaching Dimension of Linear Learners

arXiv 1512.02181 ↗First posted 7 Dec 2015cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

Teaching dimension is a learning theoretic quantity that specifies the minimum training set size to teach a target model to a learner. Previous studies on teaching dimension focused on version-space learners which maintain all hypotheses consistent with the training data, and cannot be applied to modern machine learners which select a specific hypothesis via optimization. This paper presents the first known teaching dimension for ridge regression, support vector machines, and logistic regression. We also exhibit optimal training sets that match these teaching dimensions. Our approach generalizes to other linear learners.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Dec 2015.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2018: 1; 2019: 1; 2020: 0; 2021: 6; 2022: 4; 2023: 3; 2024: 1; 2025: 3.

19 papers.

Sort:

By area:

  1. 2021Towards Understanding Knowledge Distillationcited by 158
  2. 2018Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applicationscited by 28
  3. 2019Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraintscited by 18
  4. 2021Fair Clustering Using Antidote Datacited by 10
  5. 2021Iterative Teaching by Label Synthesiscited by 10
  6. 2023Nonparametric Iterative Machine Teachingcited by 9
  7. 2022Iterative Teaching by Data Hallucinationcited by 8
  8. 2023Nonparametric Teaching for Multiple Learnerscited by 7
  9. 2021Learning Data Teaching Strategies Via Knowledge Tracingcited by 6
  10. 2025Beyond Statistical Learning: Exact Learning Is Essential for General Intelligencecited by 6
  11. 2024Representational Alignment Supports Effective Machine Teachingcited by 3
  12. 2025Policy Teaching via Data Poisoning in Learning from Human Preferencescited by 2
7 more
  1. 2021Distribution Matching for Machine Teachingcited by 1
  2. 2022Black-box Generalization of Machine Teachingcited by 1
  3. 2021Training Humans to Train Robots Dynamic Motor Skillscited by 0
  4. 2022Know Thy Student: Interactive Learning with Gaussian Processescited by 0
  5. 2022One-shot Machine Teaching: Cost Very Few Examples to Converge Fastercited by 0
  6. 2023Optimally Teaching a Linear Behavior Cloning Agentcited by 0
  7. 2025A Machine Learning Theory Perspective on Strategic Litigationcited by 0