Research map / Learning theory and algorithms / Sample complexity
Meta-learning for Mixed Linear Regression
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 |
|---|---|---|---|
| Use separate light-task batches for subspace estimation and final parameter estimation | Spectral meta-learning · Mixed linear regression meta-learning | sample complexity | Helped |
| Classify light tasks using estimated cluster parameters after heavy-task clustering | Spectral meta-learning · Mixed linear regression meta-learning | examples required per task for classification | Helped |
| Use median-of-estimates distance for clustering instead of directly applying Gaussian-mixture clustering to task estimates | Heavy-task clustering · Mixed linear regression meta-learning | sufficient examples per task for clustering | Helped |
| Use the posterior mean rather than MAP prediction | New-task prediction · Gaussian simulation with k=32 and d=256 | training and test errors | Helped |
Closest papers by meaning
- Robust Meta-learning for Mixed Linear Regression with Small Batches (NeurIPS 2020 · similarity 0.93)
- Provable Meta-Learning of Linear Representations (ICML 2021 · similarity 0.90)
- How to Distribute Data across Tasks for Meta-Learning? (AAAI 2022 · similarity 0.88)
- Learning To Learn Around A Common Mean (NeurIPS 2018 · similarity 0.87)
- Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness, and Safety (ICML 2026 · similarity 0.87)
- A Distribution-dependent Analysis of Meta Learning (ICML 2021 · 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.