A neural network (cf. Figure 1) can be thought of as a directed acyclic network consisting of

The authors contributed equally to this work 37th Conference on Neural Information Processing Systems (NeurIPS 2023). Developing upper bounds on the generalisation gap, i.e., generalisation bounds has been a longstanding topic in statistical learning.

When such components are expected to be embedded in safety-critical systems (e.g.,

Federated learning (FL) is a distributed learning framework that leverages commonalities between distributed client datasets to train a global model.

Specifically, we lay the foundation within the Bayesian framework.