提出多视图学习的新理论框架，提升模型泛化能力。
Multi-View Majority Vote Learning Algorithms: Direct Minimization of PAC-Bayesian Bounds
- 用Rényi散度构建多视图学习的泛化界，替代传统KL散度。
- 设计一阶与二阶贝叶斯边界，首次将C界扩展至多视图场景。
- 开发高效自约束优化算法，理论与实践紧密结合。
PAC-Bayesian框架显著推进了统计学习的理解，尤其在多数投票方法方面。尽管取得成功，其在多视图学习（即多个互补数据表示）中的应用仍不充分。本文将PAC-Bayesian理论拓展至多视图学习，引入基于Rényi散度的新泛化界，为传统基于Kullback-Leibler散度的方法提供替代方案，利用Rényi散度的灵活性。此外，我们提出了首类与二阶贝叶斯边界，并将C界推广至多视图设置。为连接理论与实践，设计了与理论一致的高效自约束优化算法。
原文摘要 · Abstract (English)
The PAC-Bayesian framework has significantly advanced the understanding of statistical learning, particularly for majority voting methods. Despite its successes, its application to multi-view learning -- a setting with multiple complementary data representations -- remains underexplored. In this work, we extend PAC-Bayesian theory to multi-view learning, introducing novel generalization bounds based on Rényi divergence. These bounds provide an alternative to traditional Kullback-Leibler divergence-based counterparts, leveraging the flexibility of Rényi divergence. Furthermore, we propose first- and second-order oracle PAC-Bayesian bounds and extend the C-bound to multi-view settings. To bridge theory and practice, we design efficient self-bounding optimization algorithms that align with our theoretical results.
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。