Research map / Learning theory and algorithms / Kernels and regression theory
PAC-Bayes Un-Expected Bernstein Inequality
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 the proposed un-expected Bernstein PAC-Bayes bound instead of the TS, Catoni, or Maurer bound | Regularized logistic regression · Synthetic binary classification with label noise | generalization bound | Helped |
| Use the proposed un-expected Bernstein PAC-Bayes bound instead of Maurer's bound | Regularized logistic regression · UCI binary classification datasets | generalization bound | Mixed |
| Replace the fixed prior with informed priors based on each half of the sample | PAC-Bayes bounds for sufficiently stable learning algorithms · Additional experiments (Appendix) | generalization bound | Helped |
Closest papers by meaning
- Block-Sample MAC-Bayes Generalization Bounds (ICLR 2026 · similarity 0.91)
- Toward Better PAC-Bayes Bounds for Uniformly Stable Algorithms (NeurIPS 2023 · similarity 0.90)
- PAC-Bayes Learning Bounds for Sample-Dependent Priors (NeurIPS 2020 · similarity 0.90)
- A Limitation of the PAC-Bayes Framework (NeurIPS 2020 · similarity 0.90)
- Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound (NeurIPS 2024 · similarity 0.89)
- PAC-Bayes-Chernoff bounds for unbounded losses (NeurIPS 2024 · similarity 0.88)
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.