Research map / Optimization / Optimizers
On the Stability and Generalization of Meta-Learning: the Impact of Inner-Levels
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Theoretical analysis of algorithmic stability and generalization of meta-learning algorithms, examining how the number of inner-level steps affects generalization.
Problem
Generalization of meta-learning algorithms has been studied mainly via training strategies, data splits, and looser bounds, while the effect of inner-level optimization on generalization is largely ignored.
Approach
Uses algorithmic stability analysis of several prominent meta-learning algorithms to characterize how inner-level updates impact generalization bounds.
Closest papers by meaning
- Fine-Grained Analysis of Stability and Generalization for Modern Meta Learning Algorithms (NeurIPS 2022 · similarity 0.91)
- A Closer Look at the Training Strategy for Modern Meta-Learning (NeurIPS 2020 · similarity 0.91)
- Improving Generalization of Meta-Learning With Inverted Regularization at Inner-Level (CVPR 2023 · similarity 0.91)
- On the Stability and Generalization of Meta-Learning (NeurIPS 2024 · similarity 0.90)
- Improving Generalization via Meta-Learning on Hard Samples (CVPR 2024 · similarity 0.88)
- Balanced Direction from Multifarious Choices: Arithmetic Meta-Learning for Domain Generalization (CVPR 2025 · 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.