Bayesian Multitask Learning with Latent Hierarchies

Hal Daumé

Bayesian Multitask Learning with Latent Hierarchies

Machine Learning 2009-07-07 v1

Authors: Hal Daumé

Abstract

We learn multiple hypotheses for related tasks under a latent hierarchical relationship between tasks. We exploit the intuition that for domain adaptation, we wish to share classifier structure, but for multitask learning, we wish to share covariance structure. Our hierarchical model is seen to subsume several previously proposed multitask learning models and performs well on three distinct real-world data sets.

Keywords

multi-task learning bayesian deep learning machine learning theory

Cite

@article{arxiv.0907.0783,
  title  = {Bayesian Multitask Learning with Latent Hierarchies},
  author = {Hal Daumé},
  journal= {arXiv preprint arXiv:0907.0783},
  year   = {2009}
}

Related papers

View all related →