# Optimal Cooperative Inference

arXiv: https://arxiv.org/abs/1705.08971 · HTML: https://mlsanity.com/paper/1705.08971/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 May 2017.

## Built on by (most cited first, 7 of 7)

- [Proximal Curriculum for Reinforcement Learning Agents](https://mlsanity.com/paper/2304.12877/) (2023)
- [Mitigating belief projection in explainable artificial intelligence via Bayesian Teaching](https://mlsanity.com/paper/2102.03919/) (2021)
- [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)
- [Iterative Teacher-Aware Learning](https://mlsanity.com/paper/2110.00137/) (2021)
- [Evaluating and Modeling Social Intelligence: A Comparative Study of Human and AI Capabilities](https://mlsanity.com/paper/2405.11841/) (2024)
- [Information-Theoretic Equivalence of Entropic Multi-Marginal Optimal Transport: A Theory for Multi-Agent Communication](https://mlsanity.com/paper/2208.10256/) (2022)

## Abstract (arXiv)

Cooperative transmission of data fosters rapid accumulation of knowledge by efficiently combining experiences across learners. Although well studied in human learning and increasingly in machine learning, we lack formal frameworks through which we may reason about the benefits and limitations of cooperative inference. We present such a framework. We introduce novel indices for measuring the effectiveness of probabilistic and cooperative information transmission. We relate our indices to the well-known Teaching Dimension in deterministic settings. We prove conditions under which optimal cooperative inference can be achieved, including a representation theorem that constrains the form of inductive biases for learners optimized for cooperative inference. We conclude by demonstrating how these principles may inform the design of machine learning algorithms and discuss implications for human and machine learning.