Robust Multi-Task Regression with Grossly Corrupted Observations

Abstract

We consider the multiple-response regression problem, where the response is subject to *sparse gross errors*, in the high-dimensional setup. We propose a tractable regularized M-estimator that is robust to such error, where the sum of two individual regularization terms are used: the first one encourages row-sparse regression parameters, and the second one encourages a sparse error term. We obtain non-asymptotical estimation error bounds of the proposed method. To the best of our knowledge, this is the first analysis of the robust multi-task regression problem with gross errors.

Cite

Text

Xu and Leng. "Robust Multi-Task Regression with Grossly Corrupted Observations." Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, 2012.

Markdown

[Xu and Leng. "Robust Multi-Task Regression with Grossly Corrupted Observations." Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, 2012.](https://mlanthology.org/aistats/2012/xu2012aistats-robust/)

BibTeX

@inproceedings{xu2012aistats-robust,
  title     = {{Robust Multi-Task Regression with Grossly Corrupted Observations}},
  author    = {Xu, Huan and Leng, Chenlei},
  booktitle = {Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics},
  year      = {2012},
  pages     = {1341-1349},
  volume    = {22},
  url       = {https://mlanthology.org/aistats/2012/xu2012aistats-robust/}
}