Improved Replicable Boosting with Majority-of-Majorities
Kasper Green Larsen, Markus Engelund Mathiasen, Clement Svendsen

TL;DR
This paper presents a novel replicable boosting algorithm that enhances sample efficiency by employing a two-layer majority voting scheme, building upon prior work to achieve better performance.
Contribution
The paper introduces a new two-layer majority voting boosting algorithm that improves sample complexity over previous replicable boosting methods.
Findings
Significant reduction in sample complexity compared to prior algorithms
Effective implementation of two-layer majority voting in boosting
Improved replicability in boosting algorithms
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRough Sets and Fuzzy Logic · Advanced Algebra and Logic
