[Paper] Majority-of-Three is Optimal

Source: arXiv - 2606.13614v1

Overview

We give a short proof that the majority vote of three independent consistent classifiers is an optimal learner in the realizable PAC setting. This proves optimality for the simplest voting scheme, while simplifying both the algorithmic structure and the probabilistic analysis of previous voting learners, including the algorithm of S. Hanneke and the analysis of bagging by K. Green Larsen.

Key Contributions

This paper presents research in the following areas:

• stat.ML
• cs.LG
• math.ST

Methodology

Please refer to the full paper for detailed methodology.

Practical Implications

This research contributes to the advancement of stat.ML.

Authors

• Divit Rawal
• Nikita Zhivotovskiy

Paper Information

• arXiv ID: 2606.13614v1
• Categories: stat.ML, cs.LG, math.ST
• Published: June 11, 2026
• PDF: Download PDF