Log In Sign Up

ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks

by   Jungmin Kwon, et al.

Recently, learning algorithms motivated from sharpness of loss surface as an effective measure of generalization gap have shown state-of-the-art performances. Nevertheless, sharpness defined in a rigid region with a fixed radius, has a drawback in sensitivity to parameter re-scaling which leaves the loss unaffected, leading to weakening of the connection between sharpness and generalization gap. In this paper, we introduce the concept of adaptive sharpness which is scale-invariant and propose the corresponding generalization bound. We suggest a novel learning method, adaptive sharpness-aware minimization (ASAM), utilizing the proposed generalization bound. Experimental results in various benchmark datasets show that ASAM contributes to significant improvement of model generalization performance.


page 1

page 2

page 3

page 4


Sharpness-Aware Minimization for Efficiently Improving Generalization

In today's heavily overparameterized models, the value of the training l...

Model Generalization: A Sharpness Aware Optimization Perspective

Sharpness-Aware Minimization (SAM) and adaptive sharpness-aware minimiza...

Improved Generalization Bound of Permutation Invariant Deep Neural Networks

We theoretically prove that a permutation invariant property of deep neu...

Surrogate Gap Minimization Improves Sharpness-Aware Training

The recently proposed Sharpness-Aware Minimization (SAM) improves genera...

Minimum sharpness: Scale-invariant parameter-robustness of neural networks

Toward achieving robust and defensive neural networks, the robustness ag...

Efficient Sharpness-aware Minimization for Improved Training of Neural Networks

Overparametrized Deep Neural Networks (DNNs) often achieve astounding pe...

REVE: Regularizing Deep Learning with Variational Entropy Bound

Studies on generalization performance of machine learning algorithms und...