Stress-Aware Resilient Neural Training

TL;DR

This paper proposes Stress-Aware Learning, a resilient neural training method that adaptively injects noise based on internal stress signals to improve robustness and generalization across various architectures and benchmarks.

Contribution

It introduces a novel stress-aware optimizer inspired by material science, enhancing neural training resilience by dynamically adjusting optimization behavior.

Findings

Improved robustness across six architectures and four optimizers.

Enhanced generalization on seven vision benchmarks.

Minimal computational overhead observed.

Abstract

This paper introduces Stress-Aware Learning, a resilient neural training paradigm in which deep neural networks dynamically adjust their optimization behavior - whether under stable training regimes or in settings with uncertain dynamics - based on the concept of Temporary (Elastic) and Permanent (Plastic) Deformation, inspired by structural fatigue in materials science. To instantiate this concept, we propose Plastic Deformation Optimizer, a stress-aware mechanism that injects adaptive noise into model parameters whenever an internal stress signal - reflecting stagnation in training loss and accuracy - indicates persistent optimization difficulty. This enables the model to escape sharp minima and converge toward flatter, more generalizable regions of the loss landscape. Experiments across six architectures, four optimizers, and seven vision benchmarks demonstrate improved robustness and generalization with minimal computational overhead. The code and 3D visuals will be available on GitHub: https://github.com/Stress-Aware-Learning/SAL.