Towards Robustness to Natural Variations and Distribution Shift (Student Abstract)

Download PDF
Open Webpage

Josué Martínez-Martínez, Olivia Brown, Rajmonda Caceres

Published: 2024, Last Modified: 08 Oct 2025AAAI 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: This research focuses on improving the robustness of machine learning systems to natural variations and distribution shifts. A design trade space is presented, and various methods are compared, including adversarial training, data augmentation techniques, and novel approaches inspired by model-based robust optimization formulations.