Research map / Learning theory and algorithms / Kernels and regression theory
Rademacher Complexity for Distributionally Robust Learning
Zhengyu Zhou, Weiwei Liu
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 |
|---|---|---|---|
| increase Cressie-Read parameter k (ablation) | distributionally robust linear classifier · Synthetic binary classification (d=5, hinge loss) | test risk decay rate with sample size | Improved |
| increase Cressie-Read parameter k (ablation) | distributionally robust linear classifier · Synthetic binary classification (small n) | generalization error | Hurt |
| increase feature dimension d (ablation) | distributionally robust linear classifier (k=2) · Synthetic binary classification (d=15, d=20) | distributional generalization gap | Hurt |
| add l2 regularization (ablation) | distributionally robust linear classifier (k=2) · Synthetic binary classification (n=100) | distributional generalization gap | Improved |
Closest papers by meaning
- Rademacher Complexity for Adversarially Robust Generalization (ICML 2019 · similarity 0.87)
- Adversarial Learning Guarantees for Linear Hypotheses and Neural Networks (ICML 2020 · similarity 0.86)
- Robustness Implies Generalization via Data-Dependent Generalization Bounds (ICML 2022 · similarity 0.86)
- Generalization Bounds with Minimal Dependency on Hypothesis Class via Distributionally Robust Optimization (NeurIPS 2022 · similarity 0.86)
- Universal generalization guarantees for Wasserstein distributionally robust models (ICLR 2025 · similarity 0.85)
- A New Concentration Inequality for Sampling Without Replacement and Its Application for Transductive Learning (ICML 2025 · similarity 0.85)
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.
