Research map / Learning theory and algorithms / Kernels and regression theory
Interpolation can hurt robust generalization even when there is no noise
Konstantin Donhauser, Alexandru Tifrea, Michael Aerni, Reinhard Heckel, Fanny Yang
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 |
|---|---|---|---|
| add ridge regularization instead of the max-margin (lambda to 0) interpolator in adversarial training | robust linear classification with logistic loss · noiseless synthetic data | robust risk | Improved |
| apply early stopping instead of training to the max-margin interpolator | robust linear classification · noiseless synthetic data | robust risk | Improved |
| add artificial label noise to the clean training data | robust linear classification · noiseless synthetic data | robust risk | Improved |
| add regularization when the training data is noisy | robust linear classification · noisy synthetic data | robust risk | Improved |
Closest papers by meaning
- Benign overfitting in ridge regression (JMLR 2023 · similarity 0.92)
- Benign, Tempered, or Catastrophic: Toward a Refined Taxonomy of Overfitting (NeurIPS 2022 · similarity 0.90)
- Noisy Interpolation Learning with Shallow Univariate ReLU Networks (ICLR 2024 · similarity 0.88)
- Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality (NeurIPS 2024 · similarity 0.88)
- Beyond Benign Overfitting in Nadaraya-Watson Interpolators (NeurIPS 2025 · similarity 0.88)
- Optimal Ridge Regularization for Out-of-Distribution Prediction (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.
