Research map / Learning theory and algorithms / Sample complexity
Multi-Task Learning by Maximizing Statistical Dependence
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 |
|---|---|---|---|
| Apply FSIC-based dependence maximization to heterogeneous task estimators | Independent task estimators · OSR | Kendall's Tau | Helped |
| Apply FSIC-based dependence maximization to heterogeneous task estimators | Independent task estimators · PubFig | Kendall's Tau | Helped |
| Apply FSIC-based dependence maximization to heterogeneous task estimators | Independent task estimators · Shoes | Kendall's Tau | Helped |
| Apply FSIC-based dependence maximization to heterogeneous task estimators | Independent task estimators · SUN | Kendall's Tau | Mixed |
| Apply FSIC-based dependence maximization to heterogeneous task estimators | Independent task estimators · Birds | Kendall's Tau | Mixed |
| Apply FSIC-based dependence maximization to heterogeneous task estimators | Independent task estimators · RF1 | mean squared error | Helped |
| Apply FSIC-based dependence maximization to heterogeneous task estimators | Independent task estimators · ENB | mean squared error | Mixed |
| Add sparsity regularization to selectively strengthen task dependence (ablation) | FSIC-based MTL on PubFig · PubFig | mean accuracy improvement | Helped |
| Remove sparsity regularization and uniformly strengthen all pairwise dependence (ablation) | FSIC-based MTL on PubFig · PubFig | mean accuracy improvement | Hurt |
Closest papers by meaning
- Identifying and Mitigating Spurious Correlation in Multi-Task Learning (CVPR 2025 · similarity 0.89)
- Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters (CVPR 2025 · similarity 0.88)
- Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning (ICML 2024 · similarity 0.87)
- NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective (NeurIPS 2025 · similarity 0.87)
- MTL-UE: Learning to Learn Nothing for Multi-Task Learning (ICML 2025 · similarity 0.87)
- No More Tuning: Prioritized Multi-Task Learning with Lagrangian Differential Multiplier Methods (AAAI 2025 · 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.