Self‐Certifying Classification by Linearized Deep Assignment

Abstract

AbstractWe 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.