汇报标题 (Title)：Chebyshev polynomial acceleration of stochastic Newton method for machine learning
(机械进建中随机牛顿迭代法的切比雪夫加快算法)
汇报人 (Speaker)：潘建瑜 教授（华东师范大学）
汇报功夫 (Time)：2025年10月14日(周二) 15:00
汇报地址 (Place)：校本部GJ303
约请人(Inviter)：刘巧华
主办部门：理学院数学系
汇报提要：
In this talk, we consider the acceleration of stochastic Newton method for the large scale optimization problems arising from machine learning. In order to reduce the cost of computing Hessian and Hessian inverse, we propose to utilize the Chebyshev polynomial to approximate the Hessian inverse. We show that, by utilizing the short-term recurrence formula, Chebyshev polynomial approximation can effectively reduce the computational cost. The convergence analysis are given and experiments on multiple benchmarks are carried out to illustrate the performance of our proposed acceleration method.
