Generalizing the theory of cooperative inference
2018
Cooperation
information sharingis 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 classesand 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.
Keywords:
-
Correction
-
Source
-
Cite
-
Save
43
References
2
Citations
NaN
KQI