数学科学学院

Solving Nonconvex Support Vector Machines by Alternating Direction Multiplier Methods

来源:数学科学学院 发布时间:2021-01-07   188

报告人:叶颀 教授(华南师范大学)

时间:2021年1月7日(星期四)下午3:30-4:30

地点:腾讯会议

会议ID:282 221 315

会议密码:010203

摘要:In this talk, we first present the generalized representer theorem in Banach spaces for generalized data. Based on the generalized representer theorem, we solve the nonconvex support vector machines in reproducing kernel Hilbert spaces by alternating direction multiplier methods. Next, we use the Kurdyka-Lojasiewicz inequality to prove the global convergence of the iterative solutions given by the nonconvex loss functions. Finally, we show the numerical examples of the simulated data and the real data.

联系人:郭正初(guozhengchu@zju.edu.cn


Copyright © 2020 浙江大学数学科学学院    版权所有

    浙ICP备05074421号

技术支持: 创高软件     管理登录

    您是第 1325792 位访问者