preprint · arXiv (Cornell University) · 2018

Localized Structured Prediction

Carlo Ciliberto, Francis Bach, Alessandro Rudi

Cited by 2Open access

Abstract

Key to structured prediction is exploiting the problem structure to simplify\nthe learning process. A major challenge arises when data exhibit a local\nstructure (e.g., are made by "parts") that can be leveraged to better\napproximate the relation between (parts of) the input and (parts of) the\noutput. Recent literature on signal processing, and in particular computer\nvision, has shown that capturing these aspects is indeed essential to achieve\nstate-of-the-art performance. While such algorithms are typically derived on a\ncase-by-case basis, in this work we propose the first theoretical framework to\ndeal with part-based data from a general perspective. We derive a novel\napproach to deal with these problems and study its generalization properties\nwithin the setting of statistical learning theory. Our analysis is novel in\nthat it explicitly quantifies the benefits of leveraging the part-based\nstructure of the problem with respect to the learning rates of the proposed\nestimator.\n

Cite this paper

APA 7

Ciliberto, C., Bach, F., & Rudi, A. (2018). Localized Structured Prediction. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1806.02402

MLA 9

Ciliberto, Carlo, et al. “Localized Structured Prediction.” arXiv (Cornell University), 2018, https://doi.org/10.48550/arxiv.1806.02402.

Chicago

Ciliberto, Carlo, Francis Bach, and Alessandro Rudi. 2018. “Localized Structured Prediction.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1806.02402.

Harvard

Ciliberto, C., Bach, F. and Rudi, A. (2018) ‘Localized Structured Prediction’, arXiv (Cornell University). Available at: https://doi.org/10.48550/arxiv.1806.02402.

BibTeX

@misc{ciliberto2018localized,
  title = {{Localized Structured Prediction}},
  author = {Ciliberto, Carlo and Bach, Francis and Rudi, Alessandro},
  journal = {arXiv (Cornell University)},
  year = {2018},
  doi = {10.48550/arxiv.1806.02402}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.