Improved Replicable Boosting with Majority-of-Majorities

Kasper Green Larsen, Markus Engelund Mathiasen, Clement Svendsen
1/30/2025
cs.LG

No confident code implementation found for this paper.

Abstract

We introduce a new replicable boosting algorithm which significantly improves the sample complexity compared to previous algorithms. The algorithm works by doing two layers of majority voting, using an improved version of the replicable boosting algorithm introduced by Impagliazzo et al. [2022] in the bottom layer.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

The Many Faces of Optimal Weak-to-Strong Learning

83% match2024

Improved Margin Generalization Bounds for Voting Classifiers

79% match2025

Boosting Revisited: Benchmarking and Advancing LP-Based Ensemble Methods

78% match2025

Revisiting Agnostic Boosting

76% match2025

Optimal Parallelization of Boosting

76% match1 repo2024

dVoting: Fast Voting for dLLMs

76% match1 repo312026

Cite this paper

@article{larsen2025improved,
  title  = {Improved Replicable Boosting with Majority-of-Majorities},
  author = {Kasper Green Larsen and Markus Engelund Mathiasen and Clement Svendsen},
  year   = {2025},
  eprint = {2501.18388},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.18388v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.18388.svg)](https://codeofpaper.com/paper/2501.18388)

Discussion