A Function-Centric Perspective on Flat and Sharp Minima

ArXi:2510.12451v2 Announce Type: replace-cross Flat minima are strongly associated with improved generalisation in deep neural networks. However, this connection has proven nuanced in recent studies, with both theoretical counterexamples and empirical exceptions emerging in the literature. In this paper, we revisit the role of sharpness in model performance and argue that sharpness is better understood as a function-dependent property rather than an indicator of poor generalisation.