Research map / Label-efficient and robust learning / Test-time adaptation
Out-of-Distribution Generalization via Risk Extrapolation (REx)
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use V-REx instead of ERM | Colored MNIST · Colored MNIST | test accuracy: 17.1 ± 0.6 -> 68.7 ± 0.9 | Helped |
| Use V-REx instead of IRM | Colored MNIST · Colored MNIST | test accuracy: 66.9 ± 2.5 -> 68.7 ± 0.9 | Helped |
| Use V-REx instead of MM-REx | Colored MNIST · Colored MNIST | test accuracy: 66.1 ± 1.5 -> 68.7 ± 0.9 | Mixed |
| Add V-REx risk-variance regularization | domain generalization models · Class, digit, and color imbalance CMNIST variants | accuracy | Helped |
| Add V-REx risk-variance regularization | domain generalization models · ColoredMNIST, VLCS, PACS, and OfficeHome | accuracy | No clear effect |
| Use REx in heteroskedastic tasks with differing intrinsic noise | domain generalization models · Toy structural equation models | performance | Hurt |
Closest papers by meaning
- Towards Understanding Extrapolation: a Causal Lens (NeurIPS 2024 · similarity 0.87)
- Quantifying Uncertainty in the Presence of Distribution Shifts (NeurIPS 2025 · similarity 0.87)
- Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization (NeurIPS 2024 · similarity 0.87)
- Not all distributional shifts are equal: Fine-grained robust conformal inference (ICML 2024 · similarity 0.87)
- Tolerant Algorithms for Learning with Arbitrary Covariate Shift (NeurIPS 2024 · similarity 0.86)
- Understanding Domain Generalization: A Noise Robustness Perspective (ICLR 2024 · similarity 0.86)
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.