高凯新
数学3班
发布者:赵伟翔
发布时间:2026-01-04
浏览次数:10

一、个人简介
姓名:高凯新
学历:博士
职称:讲师
邮箱:gaokaixin@ouc.edu.cn
二、研究方向
张量优化、深度学习、图像处理
三、研究成果
承担项目:
主持国家自然科学基金青年科学基金项目(C类)、山东省自然科学基金青年科学基金项目(C类)、青岛市自然科学基金青年项目、中国博士后科学基金面上资助等。
代表性论文:
K. Gao, Z.-H. Huang*, Y. Xu. Tensor robust principal component analysis based on a two-layer Tucker rank minimization model. SIAM Journal on Imaging Sciences, 2025, 18(2): 1522-1561.
K. Gao, Z.-H. Huang*, L. Guo. Low-rank matrix recovery problem minimizing a new ratio of two norms approximating the rank function then using an ADMM-type solver with applications. Journal of Computational and Applied Mathematics, 2024, 438: 115564.
X. Liu, S. Li, K. Gao*, B. Wang. A layer-wise natural gradient optimizer for training deep neural networks. Advances in Neural Information Processing Systems, 2024, 37: 28460-28489.
K. Gao, Z.-H. Huang*. Tensor robust principal component analysis via tensor fibered rank and lp minimization. SIAM Journal on Imaging Sciences, 2023, 16(1): 423-460.
K. Gao, X. Liu, Z. Huang, M. Wang, Z. Wang, D. Xu*, F. Yu. A trace-restricted Kronecker-factored approximation to natural gradient. AAAI Conference on Artificial Intelligence. 2021, 35(9): 7519-7527.


