"Improved Information-Theoretic Generalization Bounds for Distributed, " by Leighton Pate Barnes, Alex Dytso et al.
 

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

Document Type

Article

Publication Date

9-1-2022

Abstract

We consider information-theoretic bounds on the expected generalization error for statistical learning problems in a network setting. In this setting, there are K nodes, each with its own independent dataset, and the models from the K nodes have to be aggregated into a final centralized model. We consider both simple averaging of the models as well as more complicated multi-round algorithms. We give upper bounds on the expected generalization error for a variety of problems, such as those with Bregman divergence or Lipschitz continuous losses, that demonstrate an improved dependence of (Formula presented.) on the number of nodes. These “per node” bounds are in terms of the mutual information between the training dataset and the trained weights at each node and are therefore useful in describing the generalization properties inherent to having communication or privacy constraints at each node.

Identifier

85138553459 (Scopus)

Publication Title

Entropy

External Full Text Location

https://doi.org/10.3390/e24091178

e-ISSN

10994300

Issue

9

Volume

24

Grant

CCF-1908308

Fund Ref

National Science Foundation

This document is currently not available here.

Share

COinS