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 …

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 …