Research map / Learning theory and algorithms / Sample complexity
The Benefit of Multitask Representation Learning
Andreas Maurer, Massimiliano Pontil, Bernardino Romera-Paredes
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| learn a shared linear representation across tasks (MTL) instead of independent task learning | half-space learning, d=50 · synthetic half-space tasks | test classification error | Improved |
| transfer a learned dictionary to new tasks (LTL) instead of independent task learning | half-space learning · synthetic half-space, 50 new tasks | test classification error | Improved |
| overestimate dictionary size (5 atoms used, 2 true) (ablation) | MTL · synthetic half-space tasks | test classification error | Hurt |
| underestimate dictionary size (2 atoms used, 5 true) (ablation) | MTL · synthetic half-space tasks | test classification error | Hurt |
| add Gaussian label noise (ablation) | MTL · synthetic half-space tasks | test classification error | Hurt |
Closest papers by meaning
- Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks (ICML 2024 · similarity 0.89)
- Multiplicative Multitask Feature Learning (JMLR 2016 · similarity 0.88)
- Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness (JMLR 2025 · similarity 0.88)
- Learning Representation for Multitask Learning through Self-Supervised Auxiliary Learning (ECCV 2024 · similarity 0.88)
- Provable Benefit of Multitask Representation Learning in Reinforcement Learning (NeurIPS 2022 · similarity 0.87)
- An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding (AAAI 2025 · similarity 0.86)
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.
