2 papers
cs.LG2023
Stability is Stable: Connections between Replicability, Privacy, and Adaptive Generalization
Mark Bun, Marco Gaboardi, Max Hopkins +5
The notion of replicable algorithms was introduced in Impagliazzo et al. [STOC '22] to describe randomized algorithms that are stable under the resampling of their inputs. More pre…
cs.LG2023★ 1 cited
Multicalibration as Boosting for Regression
Ira Globus-Harris, Declan Harrison, Michael Kearns +2
We study the connection between multicalibration and boosting for squared error regression. First we prove a useful characterization of multicalibration in terms of a ``swap regret…