mlsanityData to 7 Oct 2026

Distribution Matching for Machine Teaching

arXiv 2105.13809 ↗First posted 6 May 2021cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Machine teaching is an inverse problem of machine learning that aims at steering the student learner towards its target hypothesis, in which the teacher has already known the student's learning parameters. Previous studies on machine teaching focused on balancing the teaching risk and cost to find those best teaching examples deriving the student model. This optimization solver is in general ineffective when the student learner does not disclose any cue of the learning parameters. To supervise such a teaching scenario, this paper presents a distribution matching-based machine teaching strategy. Specifically, this strategy backwardly and iteratively performs the halving operation on the teaching cost to find a desired teaching set. Technically, our strategy can be expressed as a cost-controlled optimization process that finds the optimal teaching examples without further exploring in the parameter distribution of the student learner. Then, given any a limited teaching cost, the training examples will be closed-form. Theoretical analysis and experiment results demonstrate this strategy.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 75 references that are in the map. First posted on arXiv 6 May 2021.

Builds on

20 of 75 references.

References · 20

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  3. 2019On The Power of Curriculum Learning in Training Deep Networkscited by 285
  4. 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 261
  5. 2017Teacher-Student Curriculum Learningcited by 197
  6. 2018Hyperbolic Entailment Cones for Learning Hierarchical Embeddingscited by 160
  7. 2019Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Costcited by 114
  8. 2018An Overview of Machine Teachingcited by 63
  9. 2018HyperML: A Boosting Metric Learning Approach in Hyperbolic Space for Recommender Systemscited by 47
  10. 2018Pool-Based Sequential Active Learning for Regressioncited by 33
  11. 2017Hyperbolic Representation Learning for Fast and Efficient Neural Question Answeringcited by 23
  12. 2021Distilling a Powerful Student Model via Online Knowledge Distillationcited by 21
8 more
  1. 2015The Teaching Dimension of Linear Learnerscited by 19
  2. 2017Towards Black-box Iterative Machine Teachingcited by 19
  3. 2013Machine Teaching for Bayesian Learners in the Exponential Familycited by 18
  4. 2017Preference-based Teachingcited by 11
  5. 2018Machine Teaching of Active Sequential Learnerscited by 11
  6. 2018An Optimal Control Approach to Sequential Machine Teachingcited by 11
  7. 2017Diameter-Based Active Learningcited by 7
  8. 2020Self-Weighted Robust LDA for Multiclass Classification with Edge Classescited by 6

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 2022Black-box Generalization of Machine Teachingcited by 1