Research map / Learning theory and algorithms / Kernels and regression theory
A Unified View on PAC-Bayes Bounds for Meta-Learning
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 MLAP-style bound with single-square classic bound (22) for meta-learning objective | MLAP-style meta-learning algorithm · MNIST 100-Swap and permuted labels | Test error (%): 100-Swap 31.4 -> 9.39; permuted labels 7.95 -> 3.1 | Helped |
| Use fast-rate bound (19) instead of classic baselines | meta-learning algorithm with fast-rate bound · MNIST 100-Swap and permuted labels | Test error (%): 100-Swap improves (31.4 -> 25.2 vs MLAP); permuted labels worsens (7.95 -> 9.77 vs MLAP) | Mixed |
| Other bounds on permuted-label task: Bound 2 and 3 of Guan et al. and λ-bound omitted from main summary | baselines · MNIST permuted labels | Test error (%) | No clear effect |
Closest papers by meaning
- Fast-Rate PAC-Bayesian Generalization Bounds for Meta-Learning (ICML 2022 · similarity 0.94)
- More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms (ICML 2024 · similarity 0.92)
- Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes (NeurIPS 2025 · similarity 0.90)
- Learning via Surrogate PAC-Bayes (NeurIPS 2024 · similarity 0.89)
- Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks (ICML 2025 · similarity 0.87)
- Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss (NeurIPS 2024 · similarity 0.87)
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.