In the PAC-Bayesian literature, the C-Bound refers to an insightful relation between the risk of a majority vote classifier (under the zero-one loss) and the first two moments of its margin (i.e., the expected margin and the voters' diversity). Until now, learning algorithms developed in this framework minimize the empirical version of the C-Bound, instead of explicit PAC-Bayesian generalization bounds. In this paper, by directly optimizing PAC-Bayesian guarantees on the C-Bound, we derive self-bounding majority vote learning algorithms. Moreover, our algorithms based on gradient descent are scalable and lead to accurate predictors paired with non-vacuous guarantees.

翻译：在PAC-Bayesian文献中,C-Bayesian文献提到多数票分类者的风险(在零一损失下)与其差值的前两个时刻(即预期差值和选民的多样性)之间的有见地关系。 到目前为止,在这个框架内开发的学习算法将C-Bayesian 的实证版本减少到最低程度,而不是明确的PAC-Bayesian 通用界限。 在本文中,通过直接优化C-Bayesian的保理,我们获得了自我约束的多数票学习算法。 此外,我们基于梯度的算法是可伸缩的,并导致精确的预测器与非真空的保证相配。