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

Josué Martínez-Martínez, Olivia Brown, Rajmonda Caceres

AAAI 2024 pp. 23579-23581

doi:10.1609/AAAI.V38I21.30481 /aaai/2024/martinezmartinez2024aaai-robustness/

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.

PDF AAAI Semantic Scholar

Cite

Text

Martínez-Martínez et al. "Towards Robustness to Natural Variations and Distribution Shift (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30481

Markdown

[Martínez-Martínez et al. "Towards Robustness to Natural Variations and Distribution Shift (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/martinezmartinez2024aaai-robustness/) doi:10.1609/AAAI.V38I21.30481

BibTeX

@inproceedings{martinezmartinez2024aaai-robustness,
  title     = {{Towards Robustness to Natural Variations and Distribution Shift (Student Abstract)}},
  author    = {Martínez-Martínez, Josué and Brown, Olivia and Caceres, Rajmonda},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {23579-23581},
  doi       = {10.1609/AAAI.V38I21.30481},
  url       = {https://mlanthology.org/aaai/2024/martinezmartinez2024aaai-robustness/}
}