Sharper information-theoretic generalization bounds for differentially private algorithms obtained via typicality arguments that improve prior mutual-information results and add new maximal-leakage bounds.
A unified framework for information-theoretic generalization bounds
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.IT 2years
2026 2representative citing papers
A unified DPI-based framework yields novel change-of-measure inequalities that produce tighter high-probability generalization bounds.
citing papers explorer
-
On the Generalization Error of Differentially Private Algorithms via Typicality
Sharper information-theoretic generalization bounds for differentially private algorithms obtained via typicality arguments that improve prior mutual-information results and add new maximal-leakage bounds.
-
Tighter Information-Theoretic Generalization Bounds via a Novel Class of Change of Measure Inequalities
A unified DPI-based framework yields novel change-of-measure inequalities that produce tighter high-probability generalization bounds.