Data Efficient and Geometric Optimal Transport Distributional Robustness for Machine Learning
Abstract
Optimal transport (OT) based distributional robustness is a promising framework for robust machine learning and laying foundation for novel regularization techniques. However, the existing OT-based distributional robustness has some severe limitations. First, it is not computationally tractable due to the min-max form. Second, it is not sufficiently rich to represent the local and global regularization, hence circumventing the applications to real-world tasks including domain adaptation, domain generalization, semi-supervised learning, and adversarial-trustworthy machine learning, which always require formulating local-global regularization terms. Targeting these severe limitations and drawbacks, we propose novel OT-based distributional robustness frameworks that are computationally tractable, sufficiently enormous to capture local-global regularizationterms, can exploit and harvest geometry structures carried in data, and can be globally sharpness-aware.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Feb 16, 2024
- Source ID
- FA23862314044
Entities
People
- Trung Le
Organizations
- Air Force Office of Scientific Research
- Monash University
- United States Air Force