SOURCE-LINKED INTELLIGENCE

On the disintegration of the stochastic majority vote: From PAC-Bayesian bounds to a self-bounding algorithm

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Weighted majority votes are central to many successful ensemble methods. PAC-Bayesian theory provides tight generalization guarantees for such models by analyzing the expected risk of stochastic classifiers, while analyzing the risk of deterministic majority votes relies on surrogate bounds. To avoid these surrogates, Zantedeschi et al. ( 2021) introduced guarantees for stochastic majority votes, but the resulting models remain randomized. In this paper, we propose a derandomization framework for stochastic majority votes. To do so, we apply recent advances in disintegrated PAC-Bayesian theory

Read original source ↗ Open in workspace

recordType

paper

region

Global