Research map / Learning theory and algorithms / Kernels and regression theory
Improved PAC-Bayesian Bounds for Linear Regression
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 the Germain et al. squared-loss complexity term with the chi-squared-MGF-based term | PAC-Bayesian linear regression bound · Linear regression under the paper's i.i.d. Gaussian assumptions | generalization-error upper bound | Helped |
| Choose a temperature parameter that scales with sample size | Improved PAC-Bayesian linear regression bound · Linear regression under the paper's i.i.d. Gaussian assumptions | asymptotic generalization-error upper bound | Helped |
| Extend the bound to account for dependence using the minimum eigenvalue of the joint input covariance | PAC-Bayesian linear regression bound · Dependent Gaussian observations, including qualifying ARX time series | applicability of the generalization bound | Helped |
Closest papers by meaning
- Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound (NeurIPS 2024 · similarity 0.89)
- PAC-Bayes Generalisation Bounds for Dynamical Systems including Stable RNNs (AAAI 2024 · similarity 0.86)
- PAC-Bayesian Error Bound, via Rényi Divergence, for a Class of Linear Time-Invariant State-Space Models (ICML 2024 · similarity 0.86)
- PAC-Bayes Bounds for Multivariate Linear Regression and Linear Autoencoders (NeurIPS 2025 · similarity 0.86)
- PAC-Bayes-Chernoff bounds for unbounded losses (NeurIPS 2024 · similarity 0.85)
- Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis (ICML 2024 · similarity 0.84)
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.