Union Support Recovery in Multi-Task Learning

Abstract

We sharply characterize the performance of different penalization schemes for the problem of selecting the relevant variables in the multi-task setting. Previous work focuses on the regression problem where conditions on the design matrix complicate the analysis. A clearer and simpler picture emerges by studying the Normal means model. This model, often used in the field of statistics, is a simplified model that provides a laboratory for studying complex procedures.

Cite

Text

Kolar et al. "Union Support Recovery in Multi-Task Learning." Journal of Machine Learning Research, 2011.

Markdown

[Kolar et al. "Union Support Recovery in Multi-Task Learning." Journal of Machine Learning Research, 2011.](https://mlanthology.org/jmlr/2011/kolar2011jmlr-union/)

BibTeX

@article{kolar2011jmlr-union,
  title     = {{Union Support Recovery in Multi-Task Learning}},
  author    = {Kolar, Mladen and Lafferty, John and Wasserman, Larry},
  journal   = {Journal of Machine Learning Research},
  year      = {2011},
  pages     = {2415-2435},
  volume    = {12},
  url       = {https://mlanthology.org/jmlr/2011/kolar2011jmlr-union/}
}