数学杂志2021，Vol.41Issue(4)：316-328,13.
多阈值和非独立同分布的在线分位数学习算法
ONLINE QUANTILE REGRESSION WITH VARYING THRESHOLDS AND NON-IDENTICAL SAMPLING DISTRIBUTIONS
摘要
Abstract
In this paper we study the online quantile regression algorithm with varying thresh-olds and non-identical sampling distributions,where at each time a sample is drawn independently from different probability distributions and the threshold values decrease with the iteration pro-cess.The learning rate of the algorithm is obtained under the assumption that the sequence of marginal distribution converges polynomially fast in the dual of a H?lder space.Several numerical simulations are presented to support our results.关键词
非一致分布/在线学习/分位数回归/再生核希尔伯特空间Key words
sampling with non-identical distributions/online learning/quantile regression/ε-insensitive pinball loss/reproducing kernel Hilbert spaces分类
数理科学引用本文复制引用
蒋铭勤..多阈值和非独立同分布的在线分位数学习算法[J].数学杂志,2021,41(4):316-328,13.基金项目
Supported by National Natural Science Foundation of China(11671307). （11671307）
