Deep Multitask Learning for Mixed-Type Outcomes with Shared Sparsity
Huichao Li, Tong Wang, Sanguo Zhang, Shuangge Ma
stat.ML, cs.LG
Submitted: 2026-07-01
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Sparse-Input Neural Networks for High-dimensional Nonparametric Regression and Classification
- Taking Advantage of Sparsity in Multi-Task Learning
- Deep Transformation Model
- From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Scalable Posterior Uncertainty for Flexible Density-Based Clustering
- A Transport Geometry of Benign Overfitting
- Efficient quadratic entropy with distance sketches