Marchand, M;
Su, H;
Morvant, E;
Rousu, J;
Shawe-Taylor, J;
(2014)
Multilabel structured output learning with random spanning trees of max-margin Markov networks.
In: Ghahramani, Z and Welling, M and Cortes, C and Lawrence, ND and Weinberger, KQ, (eds.)
[NIPS 2014: Electronic Proceedings of the 25th Neural Information Processing Systems Conference].
Preview |
Text
Marchand_Multilabel structured output learning with random spanning trees of max-margin Markov networks.pdf Download (396kB) | Preview |
Abstract
We show that the usual score function for conditional Markov networks can be written as the expectation over the scores of their spanning trees. We also show that a small random sample of these output trees can attain a significant fraction of the margin obtained by the complete graph and we provide conditions under which we can perform tractable inference. The experimental results confirm that practical learning is scalable to realistic datasets using this approach.
| Type: | Proceedings paper |
|---|---|
| Title: | Multilabel structured output learning with random spanning trees of max-margin Markov networks |
| Event: | NIPS 2014: Neural Information Processing Systems Conference, 8-13 December 2016, Montréal, Canada |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | http://papers.nips.cc/paper/5382-multilabel-struct... |
| Language: | English |
| Additional information: | Copyright © 2014 The authors |
| 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/1496469 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
