Research Interests：Big data analytic, Artificial Intelligence

Education experience：

2002.9-2006.6       Hangzhou Normal University      Mathematics  Bachelor

2006.9-2009.6       Hangzhou Normal University      Mathematics  Master

2009.9-2014.9       Xi’an Jiaotong University     Mathematics  PhD

2017.8-2019.8       City University of Hong Kong      Data Science  Advanced Scholar

Working experience：

2014-2017     Wenzhou University     Lecturer

2017-2019     Wenzhou University     Professor

2019-Present Xi’an Jiaotong University     Professor

Honors and Awards：

Teaching courses

Business Big Data Analysis

Academic Publications：

1. Shao-Bo Lin, Yunwen Lei, Ding-Xuan Zhou, Boosted Kernel Ridge Regression: Optimal Learning Rates and Early Stopping, Journal of Machine Learning Research,  20(46）(2019), 1-39.

2. Zheng-Chu Guo, Shao-Bo Lin*, Lei Shi, Distributed learning with multi-penalty regularization, Applied and Computational Harmonics Analysis, 46 (2019), 478-499.

3. Shaobo Lin, Jinshan Zeng*, Fast learning with polynomial kernels, IEEE Transactions on Cybernetics, 49 (2019),3780 - 3792.

4. Shaobo Lin, Jinshan Zeng*, Xiaoqing Zhang, Constructive neural networks learning, IEEE Transactions on Cybernetics, 49 (2019)，221-232.

5. Jian Fang， Shaobo Lin*， Zongben Xu， Learning through deterministic assignment  of hidden parameters，IEEE Transactions on Cybernetics, DOI:10.1109/TCYB.2018.2885029.

6. Shao-Bo Lin, Generalization and Expressivity for Deep Nets, IEEE Transactions on Neural Networks and Learning Systems, 30 (2019),1392 - 1406.

7. Yao Wang, Xu Liao, Shaobo Lin*, Re-scaled boosting in classification, IEEE Transactions on Neural Networks and Learning Systems, 30 (2019), 2598 - 2610. .

8. Shao-Bo Lin，Nonparametric regression using needlet kernels for spherical data，Journal of Complexity, 50 (2019) 66–83

9. Shao-Bo Lin*, Ding-Xuan Zhou, Distributed kernel gradient descent algorithms, Constructive Approximation, 47 (2018), 249-276.

10. Shao-Bo Lin*, Ding-Xuan Zhou, Optimal learning rates for kernel partial least squares, Journal of Fourier Analysis and Applications, 24 (2018), 908-933.

11. Shao-Bo Lin, Xin Guo, Ding-Xuan Zhou*，Distributed learning with regularized least squares， Journal of Machine Learning Research, 18(92) (2017), 1-31.

12. Xiangyu Chang, Shao-Bo Lin*, Ding-Xuan Zhou, Distributed semi-supervised learning with kernel ridge regression, Journal of Machine Learning Research, 18(46) (2017), 1−22.

13. Lin, Xu, Shaobo Lin, Yao Wang, Zongben Xu, Shrinkage degree in L_2 re-scale boosting for regression, IEEE Transactions on Neural Networks and Learning Systems, 28 (2017):1851-1864..

14. Shao-Bo Lin, Jinshan Zeng*, Xiangyu Chang, Learning rates for classification with Gaussian kernels, Neural Computation, 29 (2017), 3353-3380

15. Zheng-Chu Guo, Shao-Bo Lin*, Ding-Xuan Zhou, Learning theory of distributed spectral algorithms, Inverse Problems, 33 (2017), 074009.

16. Xiangyu Chang, Shao-Bo Lin*, Yao Wang, Divide and conquer local average regression, Electronic Journal of Statistics, 11 (2017), 1326-1350.

17.  Shao-Bo Lin, Limitations of shallow nets approximation, Neural Networks, 94 (2017), 96-102.

18. Jinshan Zeng, Shaobo Lin*, Zongben Xu, Sparse regularization: convergence of iterative jumping thresholding algorithm, IEEE Transactions on Signal Processing. 64 (2016), 5106-5118.

19. Shaobo Lin, Xia Liu, Jian Fang, Zongben Xu, Is extreme learning machine feasible? A theoretical assessment, (PART II), IEEE Transactions on Neural Networks and Learning System, 26 (2015), 21-34.

20. Shaobo Lin, Jinshan Zeng*, Lin Xu, Zongben Xu, Jackson-type inequalities for spherical neural networks with doubling weight, Neural Networks, 63 (2015):57-65.

Academic Projects

1. 2019.1-2022.12, Learning Theory for Deep Neural Networks, National Natural Science Foundation of China(No.61876133) , In progress, In Charge.

2. 2016.1-2018.12, Learning Theory for Distributed Supervised Learning, National Natural Science Foundation of China (No.61502342), Finished, In Charge.