Research map / Label-efficient and robust learning / Recognition and long-tail
Out-of-distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations
Aahlad Manas Puli, Lily H Zhang, Eric Karl Oermann, Rajesh Ranganath
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 |
|---|---|---|---|
| Use NURD instead of ERM | Class-Conditional Gaussians · Class-Conditional Gaussians, test | accuracy: 39\pm 0 \% -> 58 \pm 0\% | Improved |
| Use NURD instead of ERM | Colored-MNIST · Colored-MNIST, test | accuracy: 10\pm 0 \% -> 75 \pm 0 \% | Improved |
| Use reweighting NURD instead of ERM | Waterbirds · Waterbirds, test | accuracy: 66% -> 83% | Improved |
| Use reweighting NURD instead of ERM | Chest X-rays · Chest X-rays, test | accuracy: 37% -> 61% | Improved |
| Use generative NURD rather than reweighting NURD | Colored-MNIST · Colored-MNIST, test | accuracy: 75 \pm 0 \% -> 68 \pm 2\% | Hurt |
| Use generative NURD rather than reweighting NURD | Waterbirds · Waterbirds, test | accuracy | Hurt |
| Use generative NURD rather than reweighting NURD | Chest X-rays · Chest X-rays, test | accuracy | Mixed |
Closest papers by meaning
- Classification under Nuisance Parameters and Generalized Label Shift in Likelihood-Free Inference (ICML 2024 · similarity 0.85)
- Let Samples Speak: Mitigating Spurious Correlation by Exploiting the Clusterness of Samples (CVPR 2025 · similarity 0.84)
- Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization (ICML 2025 · similarity 0.83)
- Out-Of-Domain Unlabeled Data Improves Generalization (ICLR 2024 · similarity 0.83)
- Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation (ICLR 2024 · similarity 0.83)
- On the Out-of-Distribution Generalization of Self-Supervised Learning (ICML 2025 · similarity 0.83)
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.
