Research map / Learning theory and algorithms / Kernels and regression theory
Learning To Learn Around A Common Mean
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 |
|---|---|---|---|
| set splitting parameter r = 0 (use all points to test the inner algorithm) instead of larger r (ablation) | splitting stochastic meta-algorithm · synthetic Ex. 1 (common mean environment) | validation MSE | Helped |
| use intermediate split r between 0 and n-1 instead of r = 0 (ablation) | splitting stochastic meta-algorithm · synthetic Ex. 2 (two clusters) | validation MSE | Helped |
| learn common mean via LTL instead of independent task learning (ridge with h=0) | ridge regression around common mean · synthetic Ex. 2 test tasks | test MSE | Helped |
| learn common mean via LTL instead of independent task learning | ridge regression around common mean · School dataset | explained variance | Helped |
Closest papers by meaning
- Provable Meta-Learning of Linear Representations (ICML 2021 · similarity 0.90)
- A Sample Complexity Separation between Non-Convex and Convex Meta-Learning (ICML 2020 · similarity 0.89)
- Adaptive Gradient-Based Meta-Learning Methods (NeurIPS 2019 · similarity 0.89)
- Submodular Meta-Learning (NeurIPS 2020 · similarity 0.89)
- A Distribution-dependent Analysis of Meta Learning (ICML 2021 · similarity 0.88)
- Memory-Reduced Meta-Learning with Guaranteed Convergence (AAAI 2025 · similarity 0.88)
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.