Sun, S;
Shawe-Taylor, J;
Mao, L;
(2017)
PAC-Bayes analysis of multi-view learning.
Information Fusion
, 35
pp. 117-131.
10.1016/j.inffus.2016.09.008.
Preview |
Text
Final version.pdf - Accepted Version Download (308kB) | Preview |
Abstract
Multi-view learning is a widely applicable research direction. This paper presents eight PAC-Bayes bounds to analyze the generalization performance of multi-view classifiers. These bounds adopt data dependent Gaussian priors which emphasize classifiers with high view agreements. The center of the prior for the first two bounds is the origin, while the center of the prior for the third and fourth bounds is given by a data dependent vector. An important technique to obtain these bounds is two derived logarithmic determinant inequalities whose difference lies in whether the dimensionality of data is involved. The centers of the fifth and sixth bounds are calculated on a separate subset of the training set. The last two bounds use unlabeled data to represent view agreements and are thus applicable to semi-supervised multi-view learning. We evaluate all the presented multi-view PAC-Bayes bounds on benchmark data and compare them with previous single-view PAC-Bayes bounds. The usefulness and performance of the multi-view bounds are discussed.
| Type: | Article |
|---|---|
| Title: | PAC-Bayes analysis of multi-view learning |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1016/j.inffus.2016.09.008 |
| Publisher version: | http://dx.doi.org/10.1016/j.inffus.2016.09.008 |
| Language: | English |
| Additional information: | © 2016 Elsevier B.V. This manuscript version is published under a Creative Commons Attribution Non-commercial Non-derivative 4.0 International licence (CC BY-NC-ND 4.0). This licence allows you to share, copy, distribute and transmit the work for personal and non-commercial use providing author and publisher attribution is clearly stated. Further details about CC BY licences are available at http://creativecommons.org/licenses/by/4.0. Access may be initially restricted by the publisher. |
| Keywords: | PAC-Bayes bound; Statistical learning theory; Support vector machine; Multi-view learning |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/1527424 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
