论文标题
通过线性化的深层作业进行自我认证分类
Self-Certifying Classification by Linearized Deep Assignment
论文作者
论文摘要
我们提出了一类新型的深层随机预测指标，用于对PAC-Bayes风险认证范式中图的图表进行分类。分类器被实现为在随机初始条件下线性参数化的深层分配流。在最近的Pac-Bayes文献和数据依赖性先验的基础上，这种方法使（i）可以使用风险界限作为培训目标，以在假设空间上学习后验分布，（ii）能够比相关工作更有效地计算随机分类器的紧密样本外风险证书。与经验测试集的比较错误说明了这种自我认证分类方法的性能和实用性。
We propose a novel class of deep stochastic predictors for classifying metric data on graphs within the PAC-Bayes risk certification paradigm. Classifiers are realized as linearly parametrized deep assignment flows with random initial conditions. Building on the recent PAC-Bayes literature and data-dependent priors, this approach enables (i) to use risk bounds as training objectives for learning posterior distributions on the hypothesis space and (ii) to compute tight out-of-sample risk certificates of randomized classifiers more efficiently than related work. Comparison with empirical test set errors illustrates the performance and practicality of this self-certifying classification method.
