基于线性化深度赋值的自认证分类
Self-Certifying Classification by Linearized Deep Assignment
摘要：
我们提出了一类新的深度随机预测分类的PAC-贝叶斯风险认证范式内的图上的度量数据。分类器被实现为具有随机初始条件的线性参数化深度分配流。基于最近的PAC-Bayes文献和数据相关先验，这种方法使（i）使用风险边界作为训练目标，用于学习假设空间上的后验分布，以及（ii）比相关工作更有效地计算随机分类器的紧样本外风险证书。与经验测试集误差的比较说明了这种自证明分类方法的性能和实用性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
