44 citations · 62 across the 7 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022★ 6 cited
Evaluated CMI Bounds for Meta Learning: Tightness and Expressiveness
Fredrik Hellström, Giuseppe Durisi
Recent work has established that the conditional mutual information (CMI) framework of Steinke and Zakynthinou (2020) is expressive enough to capture generalization guarantees in t…
cs.LG2022★ 5 cited
A New Family of Generalization Bounds Using Samplewise Evaluated CMI
Fredrik Hellström, Giuseppe Durisi
We present a new family of information-theoretic generalization bounds, in which the training loss and the population loss are compared through a jointly convex function. This func…