A Consistent Regularization Approach for Structured Prediction
Abstract
We propose and analyze a regularization approach for structured prediction problems. We characterize a large class of loss functions that allows to naturally embed structured outputs in a linear space. We exploit this fact to design learning algorithms using a surrogate loss approach and regularization techniques. We prove universal consistency and finite sample bounds characterizing the generalization properties of the proposed method. Experimental results are provided to demonstrate the practical usefulness of the proposed approach.
Cite
Text
Ciliberto et al. "A Consistent Regularization Approach for Structured Prediction." Neural Information Processing Systems, 2016.Markdown
[Ciliberto et al. "A Consistent Regularization Approach for Structured Prediction." Neural Information Processing Systems, 2016.](https://mlanthology.org/neurips/2016/ciliberto2016neurips-consistent/)BibTeX
@inproceedings{ciliberto2016neurips-consistent,
title = {{A Consistent Regularization Approach for Structured Prediction}},
author = {Ciliberto, Carlo and Rosasco, Lorenzo and Rudi, Alessandro},
booktitle = {Neural Information Processing Systems},
year = {2016},
pages = {4412-4420},
url = {https://mlanthology.org/neurips/2016/ciliberto2016neurips-consistent/}
}