Research map / Learning theory and algorithms / Kernels and regression theory
Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes
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 shifted Rademacher processes and deviation-based symmetrization instead of standard Rademacher complexity with expectation-based symmetrization | PAC-Bayes generalization bounds · PAC-Bayes bounds | generalization-bound rate: O(m^{-1/2}) -> O(m^{-1}) | Helped |
| Add an empirical flatness term for the posterior | PAC-Bayes generalization bounds · Posteriors concentrated on sufficiently flat minima with nonzero empirical risk | bound tightness | Helped |
Closest papers by meaning
- Block-Sample MAC-Bayes Generalization Bounds (ICLR 2026 · similarity 0.90)
- A Limitation of the PAC-Bayes Framework (NeurIPS 2020 · similarity 0.89)
- PAC-Bayes-Chernoff bounds for unbounded losses (NeurIPS 2024 · similarity 0.88)
- Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss (NeurIPS 2024 · similarity 0.88)
- Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound (NeurIPS 2024 · similarity 0.88)
- Learning via Surrogate PAC-Bayes (NeurIPS 2024 · similarity 0.86)
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.