flâneur

Majority-of-Three: The Simplest Optimal Learner?

proceedings.mlr.press · 637 words · saved by 1 readers

Developing an optimal PAC learning algorithm in the realizable setting, where empirical risk minimization (ERM) is suboptimal, was a major open problem in learning theory for decades. The problem w...

[edit] Proceedings of Thirty Seventh Conference on Learning Theory, PMLR 247:22-45, 2024. Abstract Developing an optimal PAC learning algorithm in the realizable setting, where empirical risk minimization (ERM) is suboptimal, was a major open problem in learning theory for decades. The problem was finally resolved by Hanneke a few years ago. Unfortunately, Hanneke’s algorithm is quite complex as it returns the majority vote of many ERM classifiers that are trained on carefully selected subsets of the data. It is thus a natural goal to determine the simplest algorithm that is optimal. In…

saved by

related reading