Effective Gradient Sample Size via Variation Estimation for Accelerating Sharpness aware Minimization

arXiv:2403.08821v1 Announce Type: cross
Abstract: Sharpness-aware Minimization (SAM) has been proposed recently to improve model generalization ability. However, SAM calculates the gradient twice in each optimization step, thereby doubling the computation costs compared to stochastic gradient descent (SGD). In this paper, we propose a simple yet efficient sampling method to significantly accelerate SAM. Concretely, we discover that the gradient of SAM is a combination of the gradient of SGD and the Projection of the Second-order gradient matrix onto the First-order …

abstract arxiv computation costs cs.cv cs.lg gradient however model generalization optimization paper sam sample sampling simple stochastic type variation via