Improved Replicable Boosting with Majority-of-Majorities

Kasper Green Larsen, Markus Engelund Mathiasen, Clement Svendsen

Keywords: Learning theory, weak-to-strong learning, boosting, replicability, sample complexity

TL;DR: We introduce a new replicable boosting algorithm which significantly improves the sample complexity compared to previous algorithms

Abstract: We introduce a new replicable boosting algorithm which significantly improves the sample complexity compared to previous algorithms. First, we create an improved version of the replicable boosting algorithm introduced by Impagliazzo et al. (2022). We then use this algorithm with a constant accuracy parameter and run another layer of boosting on top to achieve the desired accuracy. This outer layer of boosting is inspired by the classical AdaBoost algorithm while capping the weights for a smoother distribution over the data which we show ensures replicability.

Submission Number: 149