Generalizing the theory of cooperative inference

10/04/2018
by   Pei Wang, et al.
0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

02/13/2020

Sequential Cooperative Bayesian Inference

Cooperation is often implicitly assumed when learning from other agents....
10/07/2019

A mathematical theory of cooperative communication

Cooperative communication plays a central role in theories of human cogn...
11/11/2019

Optimal partitions and Semi-discrete optimal transport

In the current book I suggest an off-road path to the subject of optimal...
07/04/2021

Rates of Estimation of Optimal Transport Maps using Plug-in Estimators via Barycentric Projections

Optimal transport maps between two probability distributions μ and ν on ...
01/22/2022

The Many Faces of Adversarial Risk

Adversarial risk quantifies the performance of classifiers on adversaria...
12/14/2020

Efficient Querying for Cooperative Probabilistic Commitments

Multiagent systems can use commitments as the core of a general coordina...
12/21/2020

Making transport more robust and interpretable by moving data through a small number of anchor points

Optimal transport (OT) is a widely used technique for distribution align...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.