# Iterative Machine Teaching

arXiv: https://arxiv.org/abs/1705.10470 · HTML: https://mlsanity.com/paper/1705.10470/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2017.

## Built on by (most cited first, 30 of 41)

- [MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models](https://mlsanity.com/paper/2309.12284/) (2023)
- [Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision](https://mlsanity.com/paper/2403.09472/) (2024)
- [Eliciting and Learning with Soft Labels from Every Annotator](https://mlsanity.com/paper/2207.00810/) (2022)
- [Interactive Teaching Algorithms for Inverse Reinforcement Learning](https://mlsanity.com/paper/1905.11867/) (2019)
- [Proximal Curriculum for Reinforcement Learning Agents](https://mlsanity.com/paper/2304.12877/) (2023)
- [Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures](https://mlsanity.com/paper/2111.15139/) (2021)
- [Nonparametric Teaching of Implicit Neural Representations](https://mlsanity.com/paper/2405.10531/) (2024)
- [Teaching an Active Learner with Contrastive Examples](https://mlsanity.com/paper/2110.14888/) (2021)
- [Reward Model Overoptimisation in Iterated RLHF](https://mlsanity.com/paper/2505.18126/) (2025)
- [Iterative Teaching by Label Synthesis](https://mlsanity.com/paper/2110.14432/) (2021)
- [Curriculum Design for Teaching via Demonstrations: Theory and Applications](https://mlsanity.com/paper/2106.04696/) (2021)
- [Nonparametric Iterative Machine Teaching](https://mlsanity.com/paper/2306.03007/) (2023)
- [Iterative Teaching by Data Hallucination](https://mlsanity.com/paper/2210.17467/) (2022)
- [Human-in-the-Loop Mixup](https://mlsanity.com/paper/2211.01202/) (2022)
- [Iterative Teacher-Aware Learning](https://mlsanity.com/paper/2110.00137/) (2021)
- [Perspectives on Incorporating Expert Feedback into Model Updates](https://mlsanity.com/paper/2205.06905/) (2022)
- [Nonparametric Teaching for Multiple Learners](https://mlsanity.com/paper/2311.10318/) (2023)
- [Proximal Curriculum with Task Correlations for Deep Reinforcement Learning](https://mlsanity.com/paper/2405.02481/) (2024)
- [Learning Data Teaching Strategies Via Knowledge Tracing](https://mlsanity.com/paper/2111.07083/) (2021)
- [Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence](https://mlsanity.com/paper/2506.23908/) (2025)
- [A Student-Teacher Architecture for Dialog Domain Adaptation under the Meta-Learning Setting](https://mlsanity.com/paper/2104.02689/) (2021)
- [Nonparametric Teaching for Graph Property Learners](https://mlsanity.com/paper/2505.14170/) (2025)
- [Agent Smith: Teaching Question Answering to Jill Watson](https://mlsanity.com/paper/2112.13677/) (2021)
- [Model Merging with Functional Dual Anchors](https://mlsanity.com/paper/2510.21223/) (2025)
- [Representational Alignment Supports Effective Machine Teaching](https://mlsanity.com/paper/2406.04302/) (2024)
- [Absolute Zero-Shot Learning](https://mlsanity.com/paper/2202.11319/) (2022)
- [L2T-DLN: Learning to Teach with Dynamic Loss Network](https://mlsanity.com/paper/2310.19313/) (2023)
- [L-WISE: Boosting Human Visual Category Learning Through Model-Based Image Selection and Enhancement](https://mlsanity.com/paper/2412.09765/) (2024)
- [Review of Hallucination Understanding in Large Language and Vision Models](https://mlsanity.com/paper/2510.00034/) (2025)
- [Human-AI Interaction Design in Machine Teaching](https://mlsanity.com/paper/2206.05182/) (2022)

## Abstract (arXiv)

In this paper, we consider the problem of machine teaching, the inverse problem of machine learning. Different from traditional machine teaching which views the learners as batch algorithms, we study a new paradigm where the learner uses an iterative algorithm and a teacher can feed examples sequentially and intelligently based on the current performance of the learner. We show that the teaching complexity in the iterative case is very different from that in the batch case. Instead of constructing a minimal training set for learners, our iterative machine teaching focuses on achieving fast convergence in the learner model. Depending on the level of information the teacher has from the learner model, we design teaching algorithms which can provably reduce the number of teaching examples and achieve faster convergence than learning without teachers. We also validate our theoretical findings with extensive experiments on different data distribution and real image datasets.