2021
DOI: 10.48550/arxiv.2110.01584
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Information-theoretic generalization bounds for black-box learning algorithms

Hrayr Harutyunyan,
Maxim Raginsky,
Greg Ver Steeg
et al.

Abstract: We derive information-theoretic generalization bounds for supervised learning algorithms based on the information contained in predictions rather than in the output of the training algorithm. These bounds improve over the existing informationtheoretic bounds, are applicable to a wider range of algorithms, and solve two key challenges: (a) they give meaningful results for deterministic algorithms and (b) they are significantly easier to estimate. We show experimentally that the proposed bounds closely follow th… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
0
0

Publication Types

Select...

Relationship

0
0

Authors

Journals

citations
Cited by 0 publications
references
References 18 publications
0
0
0
Order By: Relevance

No citations

Set email alert for when this publication receives citations?