preprint · arXiv (Cornell University) · 2018

Manifold Structured Prediction

Alessandro Rudi, Carlo Ciliberto, Gian Maria Marconi, Lorenzo Rosasco

Cited by 7Open access

Abstract

Structured prediction provides a general framework to deal with supervised problems where the outputs have semantically rich structure. While classical approaches consider finite, albeit potentially huge, output spaces, in this paper we discuss how structured prediction can be extended to a continuous scenario. Specifically, we study a structured prediction approach to manifold valued regression. We characterize a class of problems for which the considered approach is statistically consistent and study how geometric optimization can be used to compute the corresponding estimator. Promising experimental results on both simulated and real data complete our study.

Cite this paper

APA 7

Rudi, A., Ciliberto, C., Marconi, G. M., & Rosasco, L. (2018). Manifold Structured Prediction. arXiv (Cornell University).

MLA 9

Rudi, Alessandro, et al. “Manifold Structured Prediction.” arXiv (Cornell University), 2018.

Chicago

Rudi, Alessandro, Carlo Ciliberto, Gian Maria Marconi, and Lorenzo Rosasco. 2018. “Manifold Structured Prediction.” arXiv (Cornell University).

Harvard

Rudi, A. et al. (2018) ‘Manifold Structured Prediction’, arXiv (Cornell University).

BibTeX

@misc{rudi2018manifold,
  title = {{Manifold Structured Prediction}},
  author = {Rudi, Alessandro and Ciliberto, Carlo and Marconi, Gian Maria and Rosasco, Lorenzo},
  journal = {arXiv (Cornell University)},
  year = {2018}
}

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