Momentum-SAM: Sharpness Aware Minimization without Computational Overhead
This work addresses the computational bottleneck of SAM for deep neural network training, making flat minima optimization more accessible in resource-limited settings, though it is an incremental improvement.
The paper tackles the computational inefficiency of Sharpness Aware Minimization (SAM) by proposing Momentum-SAM (MSAM), which uses accumulated momentum to reduce sharpness without extra gradient calculations, achieving competitive generalization improvements with minimal overhead.
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.