发表机构
Purdue University（普渡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对VC学习的信息复杂度问题，基于CMI框架分析eCMI，构造出eCMI为O(d)的随机化5基学习器多数投票算法，成功恢复VC类的最优PAC保证。
AI 中文摘要
Steinke和Zakynthinou（2020）提出了基于算法依赖的信息论量分析学习算法信息复杂度的条件互信息（CMI）框架。我们研究其中一个量——评估条件互信息（eCMI）。一个有趣的问题是，能否通过CMI的算法依赖分析恢复VC类的最优PAC保证。我们证明可以通过构造一个学习算法来实现，该算法在可实现情况下的eCMI阶为O(d)，其中d是概念类的VC维。特别地，我们的算法是随机化的5个基学习器的多数投票，具有最优的期望泛化保证。
英文摘要
Steinke and Zakynthinou(2020) introduces the Conditional Mutual Information (CMI) framework of analyzing the information complexity of learning algorithms based on algorithm-dependent information-theoretic quantities. We study one of these quantities, the evaluated Conditional Mutual Information (eCMI). It has been an interesting question whether the optimal PAC guarantee for VC classes can be recovered from the algorithm-dependent analyses via CMI. And we show that it is possible to recover this guarantee by constructing a learning algorithm whose eCMI is of order O(d) in the realizable case, where d is the VC-dimension of the concept class. Specially, our algorithm is a randomized Majority-of-5 base learners with optimal in-expectation generalization guarantee.
