no code implementations • 27 Apr 2024 • Evzenie Coupkova, Mireille Boutin
Given a classification problem and a family of classifiers, the Rashomon ratio measures the proportion of classifiers that yield less than a given loss.
no code implementations • 11 Aug 2021 • Mireille Boutin, Evzenie Coupkova
In particular, our bounds imply that, unless the number of projections n is extremely large, there is a significant advantageous gap between the generalization error of the random projection approach and that of a linear classifier in the extended space.