Preprint
Learning the Robustness Mechanism with Bilevel Optimization
arXiv
arXiv
09/28/2026
DOI: 10.48550/arxiv.2609.35541
Abstract
We propose a distributionally robust learning framework where parameters defining the robustness mechanism are learned from held-out data instead of extensively tuned. Using bilevel optimization with both upper and lower level minimax problems, we create two instances of our framework to tackle setups with and without group labels in the training set. Theoretically, we provide sample complexity analysis for our robustness mechanism learning paradigm, showing that it achieves generalization guarantees comparable to exhaustive grid search while being more computationally efficient. Empirically, we evaluate our framework under a challenging setup when both intra-group and inter-group test distribution shifts occur at the same time, thereby demonstrating the efficacy and scalability of our method.
Details
- Title: Subtitle
- Learning the Robustness Mechanism with Bilevel Optimization
- Creators
- Yiyang Shen - University of IowaQihang Lin - University of IowaWeiran Wang - University of Iowa, Computer Science
- Resource Type
- Preprint
- Publication Details
- arXiv
- DOI
- 10.48550/arxiv.2609.35541
- ISSN
- 2331-8422
- Publisher
- arXiv
- Language
- English
- Date posted
- 09/28/2026
- Academic Unit
- Computer Science; Business Analytics
- Record Identifier
- 9985240283402771
Metrics
1 Record Views