Momentum-SAM: Sharpness Aware Minimization without Computational Overhead

TL;DR

Momentum-SAM introduces a new optimization method that achieves sharpness-aware minimization without additional computational costs, improving deep neural network training and generalization.

Contribution

The paper proposes Momentum-SAM, a novel variant of SAM that reduces computational overhead by using momentum-based parameter perturbation, enabling efficient sharpness-aware optimization.

Findings

MSAM matches SAM's generalization benefits

MSAM requires similar training time as SGD/Adam

MSAM effectively reduces overfitting

Abstract

The recently proposed optimization algorithm for deep neural networks Sharpness Aware Minimization (SAM) suggests perturbing parameters before gradient calculation by a gradient ascent step to guide the optimization into parameter space regions of flat loss. While significant generalization improvements and thus reduction of overfitting could be demonstrated, the computational costs are doubled due to the additionally needed gradient calculation, making SAM unfeasible in case of limited computationally capacities. Motivated by Nesterov Accelerated Gradient (NAG) we propose Momentum-SAM (MSAM), which perturbs parameters in the direction of the accumulated momentum vector to achieve low sharpness without significant computational overhead or memory demands over SGD or Adam. We evaluate MSAM in detail and reveal insights on separable mechanisms of NAG, SAM and MSAM regarding training optimization and generalization. Code is available at https://github.com/MarlonBecker/MSAM.