Author

Christoph H. Lampert

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint May 2026

From Privacy to Generalization: Linear Max-Information Bounds for Differentially Private Learning Algorithms

This work derives explicit upper bounds on the approximate max-information of any algorithm that fulfills $(\epsilon, \delta)$-differential privacy or R\'enyi differential privacy, thereby going beyond the classical results for pure $\epsilon$-differential privacy.

Christoph H. Lampert, Max Cairney-Leeming, Hossein Zakerinia · 0 citations