Research map / Bandits and online learning / Online convex optimization and games
Online-Within-Online 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 |
|---|---|---|---|
| Meta-learn the feature map online (ONL-ONL) instead of using the fixed identity feature map per task (ITL) | ONL-ONL · Synthetic regression, d=20, low-rank task predictors | test error (absolute loss) | Helped |
| Approximate meta-subgradients online with the inner algorithm instead of an accurate convex solver (BAT-ONL) (ablation) | ONL-ONL · Synthetic regression, d=20 | test error (absolute loss) | No clear effect |
| Online meta-learning (ONL-ONL) versus batch averaging baseline (BAT) as number of training tasks grows | ONL-ONL · Movielens-100k and Jester-1 | test error (absolute loss) | Helped |
Closest papers by meaning
- Online Constrained Meta-Learning: Provable Guarantees for Generalization (NeurIPS 2023 · similarity 0.89)
- Meta-Learning Adversarial Bandit Algorithms (NeurIPS 2023 · similarity 0.89)
- Adaptive Gradient-Based Meta-Learning Methods (NeurIPS 2019 · similarity 0.89)
- Memory Efficient Online Meta Learning (ICML 2021 · similarity 0.89)
- Online Meta-Learning (ICML 2019 · similarity 0.88)
- 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.