Research map / Learning theory and algorithms / Sample complexity
Theoretical bounds on estimation error for meta-learning
James Lucas, Mengye Ren, Irene Raissa KAMENI KAMENI, Toniann Pitassi, Richard Zemel
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 |
|---|---|---|---|
| increase meta-training data per task | Hierarchical Bayes polynomial regression · Polynomial regression | expected risk | Improved |
| increase novel-task sample size | Hierarchical Bayes polynomial regression · Polynomial regression | expected risk | Mixed |
| add more tasks rather than only more novel-task samples | Hierarchical Bayes polynomial regression · Polynomial regression | expected risk | Mixed |
| increase meta-training data per task | MAML · Sinusoid regression | average risk | Improved |
| increase novel-task sample size | MAML · Sinusoid regression | average risk | Improved |
| increase meta-training data or novel-task data | MAML · Sinusoid regression | average risk | Improved |
Closest papers by meaning
- Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis (NeurIPS 2021 · similarity 0.92)
- Fast-Rate PAC-Bayesian Generalization Bounds for Meta-Learning (ICML 2022 · similarity 0.90)
- Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stability (NeurIPS 2021 · similarity 0.89)
- Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes (NeurIPS 2025 · similarity 0.87)
- More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms (ICML 2024 · similarity 0.87)
- On the Stability and Generalization of Meta-Learning (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.
