Abstract
Pairwise learning refers to learning tasks with the associated loss functions depending on pairs of examples. Recently, pairwise learning has received increasing attention since it covers many machine learning schemes, e.g., metric learning, ranking and AUC maximization, in a unified framework. In this paper, we establish a unified generalization error bound for regularized pairwise learning without either Bernstein conditions or capacity assumptions. We apply this general result to typical learning tasks including distance metric learning and ranking, for each of which our discussion is able to improve the state-of-the-art results.
Original language | English |
---|---|
Title of host publication | Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018 |
Editors | Jerome Lang |
Publisher | International Joint Conferences on Artificial Intelligence |
Pages | 2376-2382 |
Number of pages | 7 |
ISBN (Electronic) | 9780999241127 |
DOIs | |
Publication status | Published - Jul 2018 |
Event | 27th International Joint Conference on Artificial Intelligence, IJCAI 2018 - Stockholm, Sweden Duration: 13 Jul 2018 → 19 Jul 2018 http://ijcai-18.org/ https://www.ijcai.org/proceedings/2018/ |
Publication series
Name | IJCAI International Joint Conference on Artificial Intelligence |
---|---|
Volume | 2018-July |
ISSN (Print) | 1045-0823 |
Conference
Conference | 27th International Joint Conference on Artificial Intelligence, IJCAI 2018 |
---|---|
Country/Territory | Sweden |
City | Stockholm |
Period | 13/07/18 → 19/07/18 |
Internet address |
Scopus Subject Areas
- Artificial Intelligence
User-Defined Keywords
- Kernel Methods
- Learning Preferences or Rankings
- Learning Theory
- Machine Learning