English

Adaptive and Robust Multi-Task Learning

Machine Learning 2023-09-19 v4 Machine Learning Statistics Theory Methodology Statistics Theory

Abstract

We study the multi-task learning problem that aims to simultaneously analyze multiple datasets collected from different sources and learn one model for each of them. We propose a family of adaptive methods that automatically utilize possible similarities among those tasks while carefully handling their differences. We derive sharp statistical guarantees for the methods and prove their robustness against outlier tasks. Numerical experiments on synthetic and real datasets demonstrate the efficacy of our new methods.

Keywords

Cite

@article{arxiv.2202.05250,
  title  = {Adaptive and Robust Multi-Task Learning},
  author = {Yaqi Duan and Kaizheng Wang},
  journal= {arXiv preprint arXiv:2202.05250},
  year   = {2023}
}

Comments

72 pages, 2 figures