报告题目: Pairwise learning problems with regularization networks and Nystrom subsampling approach
报告人：胡婷（西安交通大学）
报告时间：2024年4月9日10:00-11:00
报告地点：文波楼401楼会议室
摘要：Pairwise learning usually refers to the learning problem that works with pairs of training samples, such as ranking, similarity and metric learning, and AUC maximization. To overcome the challenge of pairwise learning in the large scale computation, this paper introduces Nystrom sampling approach to the coefficient-based regularized pairwise algorithm in the context of kernel networks. Our theorems establish that the obtained Nystrom estimator achieves the minimax error over all estimators using the whole data provided that the subsampling level is not too small. We derive the function relation between the subsampling level and regularization parameter that guarantees computation cost reduction and asymptotic behaviors’ optimality simultaneously. The Nystrom coefficient-based pairwise learning method does not require the kernel to be symmetric or positive semi-definite, which provides more flexibility and adaptivity in the learning process. We apply the method to the bipartite ranking problem, which improves the state-of-the-art theoretical results in previous works.
报告人简介：胡婷，西安交通大学管理学院教授，博士生导师，主要从事机器学习领域中数学问题和学习算法的理论研究。现阶段已在应用数学和机器学习领域中有影响力的期刊上发表了一系列学术论文，主要包括Applied and Computational Harmonic Analysis，Journal of Machine Learning Research，IEEE Transactions on Signal Processing，Inverse Problems，Constructive Approximation, Neural Networks, Journal of Multivariate Analysis等。
