郑州大学学报（理学版）2025，Vol.57Issue(4)：55-62,8.DOI:10.13705/j.issn.1671-6841.2023199
"可预测的"非凸在线点对学习的遗憾界
Regret Bounds for Online Pairwise Learning with Predictable Non-convex Loss Functions
摘要
Abstract
Online pairwise learning is a machine learning model in which the loss functions depend on a pair of instances.Generalization is an important aspect of online pairwise learning theory research.Most of the existing works on online pairwise learning used adversarial loss functions and provided regret bounds on-ly with convex loss functions.However,convexity was not typically applicable in practical scenarios.For non-convex online pairwise learning,the regret bound of online pairwise learning with a"predictable"loss function based on stability analysis was provided and the corresponding stability analysis was conducted.Through the relationship between stability and regret,a common way to measure the generalization ability of online pairwise learning,the regret bound was established with a"predictable"non-convex loss function.It was proved that when the learner obtained an offline oracle,"predictable"non-convex generalized online pairwise learning reached the regret bound of O(T-3/2).This study enriched the theoretical research on non-convex online pairwise learning and was superior to the existing theoretical guarantees.关键词
在线点对学习/非凸/稳定性/遗憾界/离线神谕Key words
online pairwise learning/non-convex/stability/regret bounds/offline optimization oracle分类
计算机与自动化引用本文复制引用
郎璇聪,王梅,刘勇,李春生.."可预测的"非凸在线点对学习的遗憾界[J].郑州大学学报（理学版）,2025,57(4):55-62,8.基金项目
国家自然科学基金项目(51774090,62076234) （51774090,62076234）
黑龙江省博士后科研启动金资助项目(LBH-Q20080) （LBH-Q20080）
黑龙江省研究生精品课程建设项目(15141220103) （15141220103）
