On the Rashomon ratio of infinite hypothesis sets

arXiv:2404.17746v1 Announce Type: new
Abstract: Given a classification problem and a family of classifiers, the Rashomon ratio measures the proportion of classifiers that yield less than a given loss. Previous work has explored the advantage of a large Rashomon ratio in the case of a finite family of classifiers. Here we consider the more general case of an infinite family. We show that a large Rashomon ratio guarantees that choosing the classifier with the best empirical accuracy among a random …

abstract arxiv case classification classifiers cs.lg family hypothesis loss math.pr stat.ml type work