LGJan 30, 2025
Improved Replicable Boosting with Majority-of-Majorities
arXiv:2501.18388v21 citationsh-index: 3
AI Analysis
This work addresses the challenge of replicability in boosting algorithms, which is important for researchers and practitioners in machine learning, though it appears incremental as it builds on prior work.
The paper tackles the problem of replicable boosting by introducing a new algorithm that uses two layers of majority voting, resulting in significantly improved sample complexity compared to previous methods.
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.