Research map / Label-efficient and robust learning / Recognition and long-tail
Robust Generalization despite Distribution Shift via Minimum Discriminating Information
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 MDI-DRO instead of ERM under covariate shift | Logistic regression · Synthetic covariate shift | out-of-sample risk | Helped |
| Use MDI-DRO instead of ERM under covariate shift | Logistic regression · Synthetic covariate shift | out-of-sample risk variance | Helped |
| Use MDI-DRO instead of IWERM without assuming test-distribution importance weights | Logistic regression · Synthetic covariate shift | out-of-sample risk variance | Helped |
| Use MDI-DRO instead of IWERM without assuming test-distribution importance weights | Logistic regression · Synthetic covariate shift | out-of-sample risk | No clear effect |
| Use MDI-DRO rather than ERM on the biased training sample | Heart disease classification · Heart disease classification with sample bias | misclassification rate | Mixed |
| Use MDI-DRO for off-policy evaluation at small ambiguity radii | Inventory control OPE · Inventory control OPE | estimation accuracy | Helped |
| Use MDI-DRO for off-policy evaluation at small ambiguity radii | Inventory control OPE · Inventory control OPE | estimation precision | Helped |
| Increase the regularization radius r | MDI-DRO · Synthetic covariate shift | upper confidence bound reliability | Helped |
Closest papers by meaning
- Universal generalization guarantees for Wasserstein distributionally robust models (ICLR 2025 · similarity 0.89)
- Towards Robust Out-of-Distribution Generalization Bounds via Sharpness (ICLR 2024 · similarity 0.88)
- Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization (NeurIPS 2024 · similarity 0.88)
- Structure-informed Risk Minimization for Robust Ensemble Learning (ICML 2025 · similarity 0.87)
- Tolerant Algorithms for Learning with Arbitrary Covariate Shift (NeurIPS 2024 · similarity 0.87)
- Multiply Robust Estimation for Local Distribution Shifts with Multiple Domains (ICML 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.