Research map / Learning theory and algorithms / Kernels and regression theory
Robustness Implies Generalization via Data-Dependent Generalization Bounds
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 |
|---|---|---|---|
| Replace sqrt(K) covering-number dependence with data-dependent |T_S| (number of partition cells hit by training data) | algorithmic robustness generalization bound · synthetic and real-world data, epsilon-covering partition | size of |T_S| relative to K | Helped |
| Replace global loss bound B with per-hypothesis max loss zeta(A_S) (ablation) | algorithmic robustness generalization bound · theoretical | bound tightness | Helped |
| Random projection to reduce K before the partition | partition for the proposed bound · real-world (MNIST etc.) | |T_S| relative to K | No clear effect |
Closest papers by meaning
- Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Power (ICLR 2025 · similarity 0.90)
- Towards Robust Out-of-Distribution Generalization Bounds via Sharpness (ICLR 2024 · similarity 0.90)
- Algorithmic Stability Unleashed: Generalization Bounds with Unbounded Losses (ICML 2024 · similarity 0.89)
- Universal generalization guarantees for Wasserstein distributionally robust models (ICLR 2025 · similarity 0.89)
- Towards Generalization beyond Pointwise Learning: A Unified Information-theoretic Perspective (ICML 2024 · similarity 0.89)
- Fantastic Generalization Measures are Nowhere to be Found (ICLR 2024 · similarity 0.89)
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.