# Generalizing the theory of cooperative inference

arXiv: https://arxiv.org/abs/1810.02423 · HTML: https://mlsanity.com/paper/1810.02423/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2018.

## Built on by (most cited first, 4 of 4)

- [Iterative Teaching by Label Synthesis](https://mlsanity.com/paper/2110.14432/) (2021)
- [Iterative Teacher-Aware Learning](https://mlsanity.com/paper/2110.00137/) (2021)
- [Discrete Probabilistic Inverse Optimal Transport](https://mlsanity.com/paper/2112.09754/) (2021)
- [Information-Theoretic Equivalence of Entropic Multi-Marginal Optimal Transport: A Theory for Multi-Agent Communication](https://mlsanity.com/paper/2208.10256/) (2022)

## Abstract (arXiv)

Cooperation information sharing is important to theories of human learning and has potential implications for machine learning. Prior work derived conditions for achieving optimal Cooperative Inference given strong, relatively restrictive assumptions. We relax these assumptions by demonstrating convergence for any discrete joint distribution, robustness through equivalence classes and stability under perturbation, and effectiveness by deriving bounds from structural properties of the original joint distribution. We provide geometric interpretations, connections to and implications for optimal transport, and connections to importance sampling, and conclude by outlining open questions and challenges to realizing the promise of Cooperative Inference.