🤖 machine learning
A Function-Centric Perspective on Flat and Sharp Minima
This paper challenges the conventional view that flat minima inherently ensure better generalization, arguing through extensive empirical studies that sharpness is a function-dependent property — sharper minima often correlate with improved performance, robustness, and calibration when models are properly regularized, though distinguishing task-driven sharpness from memorization-driven sharpness remains an open practical question.