Research map / Learning theory and algorithms / Kernels and regression theory
Consistent Multitask Learning with Nonlinear Output Relations
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 nonlinear output constraints to capture relations among tasks | NL-MTL · Synthetic circumference and lemniscate | MSE | Helped |
| Use nonlinear constraints for robot-joint torque tasks | NL-MTL[R] · Sarcos | explained variance (%): 50.3 -> 55.4 | Helped |
| Use nonlinear constraints for robot-joint torque tasks | NL-MTL[P] · Sarcos | explained variance (%): 50.3 -> 54.6 | Helped |
| Enforce logical consistency among pairwise movie comparisons | NL-MTL · Movielens100k | weighted rank error: 0.396 -> 0.321 | Helped |
| Use true multitask learning with missing pairwise labels instead of filling missing outputs with 0 | Ranking SELF estimator · Movielens100k | weighted rank error: 0.396 -> 0.321 | Helped |
Closest papers by meaning
- Progressive Multi-task Learning with Controlled Information Flow for Joint Entity and Relation Extraction (AAAI 2021 · similarity 0.87)
- Multitask Learning with No Regret: from Improved Confidence Bounds to Active Learning (NeurIPS 2023 · similarity 0.86)
- Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks (ICML 2024 · similarity 0.86)
- Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters (CVPR 2025 · similarity 0.85)
- NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective (NeurIPS 2025 · similarity 0.85)
- Towards Principled Task Grouping for Multi-Task Learning (NeurIPS 2026 · similarity 0.85)
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.