Research map / Optimization / Optimizers
Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters
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 |
|---|---|---|---|
| increase inner-loop gradient steps N (strongly-convex inner loss) (ablation) | ANIL · FC100 and miniImageNet, 5-way 5-shot | convergence rate per meta-iteration | Helped |
| increase inner-loop gradient steps N (nonconvex inner loss) (ablation) | ANIL · FC100 and miniImageNet, 5-way 5-shot | convergence rate | Hurt |
| update only the head in the inner loop (ANIL) instead of all parameters (MAML) | MAML · FC100 and miniImageNet | accuracy versus running time | Helped |
| use mini-batch SGD instead of Adam for the outer loop (ablation) | ANIL · FC100 | convergence behaviour | No clear effect |
Closest papers by meaning
- Meta-Learning with Neural Tangent Kernels (ICLR 2021 · similarity 0.90)
- Unraveling Model-Agnostic Meta-Learning via The Adaptation Learning Rate (ICLR 2022 · similarity 0.90)
- Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML (ICLR 2020 · similarity 0.89)
- First-order ANIL provably learns representations despite overparametrisation (ICLR 2024 · similarity 0.89)
- Memory-Reduced Meta-Learning with Guaranteed Convergence (AAAI 2025 · similarity 0.89)
- Provable Meta-Learning with Low-Rank Adaptations (NeurIPS 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.