Conditional Teaching Size
Not on the map. Why?
Abstract (arXiv)
Recent research in machine teaching has explored the instruction of any concept expressed in a universal language. In this compositional context, new experimental results have shown that there exist data teaching sets surprisingly shorter than the concept description itself. However, there exists a bound for those remarkable experimental findings through teaching size and concept complexity that we further explore here. As concepts are rarely taught in isolation we investigate the best configuration of concepts to teach a given set of concepts, where those that have been acquired first can be reused for the description of new ones. This new notion of conditional teaching size uncovers new insights, such as the interposition phenomenon: certain prior knowledge generates simpler compatible concepts that increase the teaching size of the concept that we want to teach. This does not happen for conditional Kolmogorov complexity. Furthermore, we provide an algorithm that constructs optimal curricula based on interposition avoidance. This paper presents a series of theoretical results, including their proofs, and some directions for future work. New research possibilities in curriculum teaching in compositional scenarios are now wide open to exploration.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 43 references that are in the map. First posted on arXiv 29 Jun 2021.
Builds on
16 of 43 references.
References · 16
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2020Measuring Massive Multitask Language Understandingcited by 7,768
- 2021Curriculum Learning: A Surveycited by 257
- 2018Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networkscited by 113
- 2019Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Datacited by 103
- 2020Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learningcited by 81
- 2020Learning Compositional Rules via Neural Program Synthesiscited by 74
- 2020SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teachingcited by 71
- 2014Curriculum Learning of Multiple Taskscited by 65
- 2018An Overview of Machine Teachingcited by 63
- 2017Iterative Machine Teachingcited by 40
4 more
- 2020A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognitioncited by 12
- 2017Preference-based Teachingcited by 11
- 2020Conversation Learner -- A Machine Teaching Tool for Building Dialog Managers for Task-Oriented Dialog Systemscited by 9
- 2020Perspective Plane Program Induction from a Single Imagecited by 9
Built on by
Not cited yet.