Generalization Bounds for Regularized Pairwise Learning

Generalization Bounds for Regularized Pairwise Learning

Yunwen Lei, Shao-Bo Lin, Ke Tang

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Main track. Pages 2376-2382. https://doi.org/10.24963/ijcai.2018/329

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. 
Keywords:
Machine Learning: Kernel Methods
Machine Learning: Learning Preferences or Rankings
Machine Learning: Learning Theory
Machine Learning: Machine Learning