A Functional Extension of Multi-Output Learning

Abstract

When considering simultaneously a finite number of tasks, multi-output learning enables one to account for the similarities of the tasks via appropriate regularizers. We propose a generalization of the classical setting to a continuum of tasks by using vector-valued RKHSs.

Cite

Text

Lambert et al. "A Functional Extension of Multi-Output Learning." ICML 2019 Workshops: AMTL, 2019.

Markdown

[Lambert et al. "A Functional Extension of Multi-Output Learning." ICML 2019 Workshops: AMTL, 2019.](https://mlanthology.org/icmlw/2019/lambert2019icmlw-functional/)

BibTeX

@inproceedings{lambert2019icmlw-functional,
  title     = {{A Functional Extension of Multi-Output Learning}},
  author    = {Lambert, Alex and Brault, Romain and Szabo, Zoltan and d'Alche-Buc, Florence},
  booktitle = {ICML 2019 Workshops: AMTL},
  year      = {2019},
  url       = {https://mlanthology.org/icmlw/2019/lambert2019icmlw-functional/}
}