Saved in:
Bibliographic Details
Main Authors: Shakarami, Ashkan, Yeganeh, Yousef, Farshad, Azade, Nicole, Lorenzo, Ghidoni, Stefano, Navab, Nassir
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.00098
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916874887888896
author Shakarami, Ashkan
Yeganeh, Yousef
Farshad, Azade
Nicole, Lorenzo
Ghidoni, Stefano
Navab, Nassir
author_facet Shakarami, Ashkan
Yeganeh, Yousef
Farshad, Azade
Nicole, Lorenzo
Ghidoni, Stefano
Navab, Nassir
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00098
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stress-Aware Resilient Neural Training
Shakarami, Ashkan
Yeganeh, Yousef
Farshad, Azade
Nicole, Lorenzo
Ghidoni, Stefano
Navab, Nassir
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
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.
title Stress-Aware Resilient Neural Training
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.00098