preprint · arXiv (Cornell University) · 2018

Multiview Learning of Weighted Majority Vote by Bregman Divergence Minimization

Anil Goyal, Emilie Morvant, Massih-Reza Amini

Cited by 0Open access

Abstract

We tackle the issue of classifier combinations when observations have multiple views. Our method jointly learns view-specific weighted majority vote classifiers (i.e. for each view) over a set of base voters, and a second weighted majority vote classifier over the set of these view-specific weighted majority vote classifiers. We show that the empirical risk minimization of the final majority vote given a multiview training set can be cast as the minimization of Bregman divergences. This allows us to derive a parallel-update optimization algorithm for learning our multiview model. We empirically study our algorithm with a particular focus on the impact of the training set size on the multiview learning results. The experiments show that our approach is able to overcome the lack of labeled information.

Cite this paper

APA 7

Goyal, A., Morvant, E., & Amini, M.-R. (2018). Multiview Learning of Weighted Majority Vote by Bregman Divergence Minimization. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1805.10212

MLA 9

Goyal, Anil, et al. “Multiview Learning of Weighted Majority Vote by Bregman Divergence Minimization.” arXiv (Cornell University), 2018, https://doi.org/10.48550/arxiv.1805.10212.

Chicago

Goyal, Anil, Emilie Morvant, and Massih-Reza Amini. 2018. “Multiview Learning of Weighted Majority Vote by Bregman Divergence Minimization.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1805.10212.

Harvard

Goyal, A., Morvant, E. and Amini, M.-R. (2018) ‘Multiview Learning of Weighted Majority Vote by Bregman Divergence Minimization’, arXiv (Cornell University). Available at: https://doi.org/10.48550/arxiv.1805.10212.

BibTeX

@misc{goyal2018multiview,
  title = {{Multiview Learning of Weighted Majority Vote by Bregman Divergence Minimization}},
  author = {Goyal, Anil and Morvant, Emilie and Amini, Massih-Reza},
  journal = {arXiv (Cornell University)},
  year = {2018},
  doi = {10.48550/arxiv.1805.10212}
}

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