Multi-task Highly Adaptive Lasso
Not on the map. Why?
Abstract (arXiv)
We propose a novel, fully nonparametric approach for the multi-task learning, the Multi-task Highly Adaptive Lasso (MT-HAL). MT-HAL simultaneously learns features, samples and task associations important for the common model, while imposing a shared sparse structure among similar tasks. Given multiple tasks, our approach automatically finds a sparse sharing structure. The proposed MTL algorithm attains a powerful dimension-free convergence rate of op(n-1/4) or better. We show that MT-HAL outperforms sparsity-based MTL competitors across a wide range of simulation studies, including settings with nonlinear and linear relationships, varying levels of sparsity and task correlations, and different numbers of covariates and sample size.
Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 12 of its 34 references that are in the map. First posted on arXiv 27 Jan 2023.
Builds on
12 of 34 references.
References · 12
- 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,348
- 2019A Comprehensive Survey on Transfer Learningcited by 1,157
- 2017A Survey on Multi-Task Learningcited by 840
- 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 799
- 2016Cross-stitch Networks for Multi-task Learningcited by 466
- 2020Multi-Task Learning with Deep Neural Networks: A Surveycited by 375
- 2019Multi-Task Deep Neural Networks for Natural Language Understandingcited by 350
- 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 169
- 2020A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Taskscited by 51
- 2019Learning Sparse Sharing Architectures for Multiple Taskscited by 31
- 2022Multi-Task Learning for Visual Scene Understandingcited by 6
- 2022Lassoed Tree Boostingcited by 4
Built on by
Not cited yet.