Conditionally Gaussian PAC-Bayes

Eugenio Clerico · George Deligiannidis · Arnaud Doucet

[ Abstract ]
Mon 28 Mar 4:30 a.m. PDT — 6 a.m. PDT


Recent studies have empirically investigated different methods to train stochastic neural networks on a classification task by optimising a PAC-Bayesian bound via stochastic gradient descent. Most of these procedures need to replace the misclassification error with a surrogate loss, leading to a mismatch between the optimisation objective and the actual generalisation bound. The present paper proposes a novel training algorithm that optimises the PAC-Bayesian bound, without relying on any surrogate loss. Empirical results show that this approach outperforms currently available PAC-Bayesian training methods.

Chat is not available.