Improved Information-Theoretic Generalization Bounds for Distributed, Federated, and Iterative Learning

Improved Information-Theoretic Generalization Bounds for Distributed, Federated, and Iterative Learning

We consider information-theoretic bounds on the expected generalization error for statistical learning problems in a network setting. In this setting, there are <i>K</i> nodes, each with its own independent dataset, and the models from the <i>K</i> nodes have to be aggregated...

Full description

Bibliographic Details
Main Authors: Leighton Pate Barnes, Alex Dytso, Harold Vincent Poor
Format: Article
Language:English
Published: MDPI AG 2022-08-01
Series:Entropy
Subjects:
generalization error
information-theoretic bounds
distribution and federated learning
Online Access:https://www.mdpi.com/1099-4300/24/9/1178

Internet

https://www.mdpi.com/1099-4300/24/9/1178

Similar Items