Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice
Jonas Rothfuss, Martin Josifoski, Vincent Fortuin, Andreas Krause
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 |
|---|---|---|---|
| use PACOH bound instead of earlier meta-learning bound in classification | PAC-Bayesian meta-learning bound · Binary classification (m=5) | bound tightness: non-vacuous for more than 30 meta-training tasks | Improved |
| increase hyper-prior misspecification relative to true task mean (ablation) | meta-learning vs per-task bound · Linear regression (d=10, m=5) | improvement of meta-learning bound over per-task bound | Improved |
| increase hyper-prior variance (less informative hyper-prior) (ablation) | meta-learning vs per-task bound · Linear regression (d=10, m=5) | improvement of meta-learning bound over per-task bound: provable improvement with only 10--20 meta-training tasks | Improved |
Closest papers by meaning
- PACOH: Bayes-Optimal Meta-Learning with PAC-Guarantees (ICML 2021 · similarity 0.97)
- More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms (ICML 2024 · similarity 0.94)
- Fast-Rate PAC-Bayesian Generalization Bounds for Meta-Learning (ICML 2022 · similarity 0.93)
- Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss (NeurIPS 2024 · similarity 0.91)
- Learning via Surrogate PAC-Bayes (NeurIPS 2024 · similarity 0.90)
- Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks (ICML 2025 · 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.
