Research map / Label-efficient and robust learning / OOD and anomaly detection
Towards a Theoretical Framework of Out-of-Distribution Generalization
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 |
|---|---|---|---|
| select models by validation accuracy minus a feature-variation penalty instead of validation accuracy alone | DomainBed model selection (ERM, CORAL, Mixup, GroupDRO, IRM candidates) · PACS | avg OOD accuracy: 84.91 -> 86.57 | Helped |
| select models by validation accuracy minus a feature-variation penalty instead of validation accuracy alone | DomainBed model selection · OfficeHome | avg OOD accuracy: 67.09 -> 68.09 | Helped |
| select models by validation accuracy minus a feature-variation penalty instead of validation accuracy alone | DomainBed model selection · VLCS | avg OOD accuracy: 75.69 -> 76.32 | Helped |
| select models by variation-penalized criterion on a single unseen domain | DomainBed model selection · OfficeHome unseen domain C | OOD accuracy: 55.56 -> 55.07 | Hurt |
Closest papers by meaning
- Bridging OOD Detection and Generalization: A Graph-Theoretic View (NeurIPS 2024 · similarity 0.90)
- OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable? (ICML 2025 · similarity 0.90)
- Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations (NeurIPS 2025 · similarity 0.89)
- Towards Robust Out-of-Distribution Generalization Bounds via Sharpness (ICLR 2024 · similarity 0.89)
- The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection (NeurIPS 2024 · similarity 0.89)
- Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the Role of Model Complexity (NeurIPS 2025 · similarity 0.88)
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.