Research map / Label-efficient and robust learning / Test-time adaptation
Probable Domain Generalization via Quantile Risk Minimization
Cian Eastwood, Alexander Robey, Shashank Singh, Julius Von Kügelgen, Hamed Hassani, George J. Pappas, Bernhard Schölkopf
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Optimize an estimated α-quantile of risk across training domains rather than average risk | ERM-style domain generalization · iWildCam | 0.90 quantile risk: 2.73 -> 1.81 | Improved |
| Optimize an estimated α-quantile of risk across training domains rather than average risk | ERM-style domain generalization · OGB-MolPCBA | 1.0 quantile risk: 16.04 -> 7.16 | Improved |
| Optimize an estimated α-quantile of risk across training domains rather than average risk | ERM-style domain generalization · OGB-MolPCBA | mean risk: 0.051 -> 0.053 | Hurt |
| Vary α from 0.25 to 0.99 (ablation) | EQRM · iWildCam | 0.90 quantile risk: 3.48 -> 1.81 | Mixed |
| Vary α from 0.25 to 0.99 (ablation) | EQRM · OGB-MolPCBA | 1.0 quantile risk: 15.46 -> 7.16 | Mixed |
| Add ERM pretraining before the DG penalty (ablation) | ColoredMNIST DG methods · ColoredMNIST | test accuracy | Improved |
| Increase α toward 1 (ablation) | EQRM · ColoredMNIST | cross-domain accuracy consistency | Improved |
| Use KDE smoothing to estimate risk distributions (ablation) | EQRM · Domain generalization | tail-risk extrapolation | Improved |
Closest papers by meaning
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.88)
- Set Valued Predictions For Robust Domain Generalization (ICML 2025 · similarity 0.88)
- Understanding Domain Generalization: A Noise Robustness Perspective (ICLR 2024 · similarity 0.87)
- Lost Domain Generalization Is a Natural Consequence of Lack of Training Domains (AAAI 2024 · similarity 0.87)
- QT-DoG: Quantization-Aware Training for Domain Generalization (ICML 2025 · similarity 0.87)
- Rethinking Multi-domain Generalization with A General Learning Objective (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
