Lower expected Fisher rank implies better PAC generalization

Summary

Deep learning architectures tend to generalize well to unseen data, but explaining this capability is still an open area of research. Under the assumption of i.i.d. data, PAC-Bayes provides a bound on generalization error, and its tightness relies on a parameter distribution that covers a large volume of low-loss solutions. The Fisher information metric endows the parameter space with a geometry for which distances reflect functional changes, and whose zero-component captures functional invariances. We define and study a Fisher-aligned parameter distribution for which we can simultaneously guarantee (1) a low-loss, thanks to the exploration constrained on the functional invariances and (2) a large log-volume of parameters, proportional to the number of zero eigenvalues. This distribution results in a high-probability generalization error bound, which scales with the expected rank of the Fisher information matrix, shedding light on the relevance of this quantity.