首次给出投票分类器的紧致边界，揭示了模型复杂度与泛化性能的关系。

Tight Margin-Based Generalization Bounds for Voting Classifiers over Finite Hypothesis Sets

• 基于边际构造新的泛化界，适用于有限假设集的投票分类器。
• 边界在训练样本数、假设集大小等参数间达到最优权衡。
• 对理解集成学习的泛化能力有重要价值，适合理论研究者阅读。

我们首次为投票分类器证明了基于边际的泛化界，该界在假设集规模、边际大小、具有给定边际的训练点比例、训练样本数量以及出错概率之间的权衡上是渐近紧致的。

原文摘要 · Abstract (English)

We prove the first margin-based generalization bound for voting classifiers, that is asymptotically tight in the tradeoff between the size of the hypothesis set, the margin, the fraction of training points with the given margin, the number of training samples and the failure probability.

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。