Multitask Regression with Pairwise Fusion
Abstract
We study multitask regression when coefficient sharing can differ by predictor. For a given predictor, many tasks may have the same coefficient while a few differ, and the exceptional tasks need not be the same for another predictor. We describe this structure by two quantities: the number of active predictors and the total number of task coefficients that differ from the most common value for their predictor. We estimate the coefficient matrix by penalizing all pairwise coefficient differences across tasks, with an additional group penalty when predictor selection is needed. The resulting upper and lower bounds have the same dependence on these two quantities. We also consider the stronger setting in which a large set of tasks shares one entire coefficient vector. Under explicit sample-size conditions, the same pairwise estimator pools those tasks exactly, while allowing the remaining tasks to differ. Simulations and household energy data illustrate the transition between broad sharing and task-specific coefficients.
Related
- PaCMoE: Pairwise Cross-Modal Attention Fusion with Mixture-of-Experts for Stock Movement Prediction
- Adaptive Conformal Prediction for Image Regression Models with Application to an Inertial Confinement Fusion Emulator
- Geotechnically Informed Monitoring-Data Fusion and Gradient-Boosted Regression for Instrumented Driven Piles
- The Geometry of Multitask Learning: Sharp Rates for Shared Subspace Estimation
- Optimal Multitask Representations Under a Rate Constraint: An Information Bottleneck Analysis
BibTeX
@misc{li2026multitask,
title = {{Multitask Regression with Pairwise Fusion}},
author = {Xiaodong Li and Zhentao Li},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.27280},
eprint = {2609.27280},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.27280},
}
RIS
TY - UNPB
TI - Multitask Regression with Pairwise Fusion
AU - Xiaodong Li
AU - Zhentao Li
PY - 2026
DA - 2026/09/23
PB - arXiv
DO - 10.48550/arxiv.2609.27280
UR - https://arxiv.org/abs/2609.27280
AB - We study multitask regression when coefficient sharing can differ by predictor. For a given predictor, many tasks may have the same coefficient while a few differ, and the exceptional tasks need not be the same for another predictor. We describe this structure by two quantities: the number of active predictors and the total number of task coefficients that differ from the most common value for their predictor. We estimate the coefficient matrix by penalizing all pairwise coefficient differences across tasks, with an additional group penalty when predictor selection is needed. The resulting upper and lower bounds have the same dependence on these two quantities. We also consider the stronger setting in which a large set of tasks shares one entire coefficient vector. Under explicit sample-size conditions, the same pairwise estimator pools those tasks exactly, while allowing the remaining tasks to differ. Simulations and household energy data illustrate the transition between broad sharing and task-specific coefficients.
ER -