Basic Information
Shaogao Lv is a Professor at Southeast University. He received his Ph.D. in Science from both City University of Hong Kong and University of Science and Technology of China in 2011, with research focus on statistical learning theory. From 2011 to 2018, he served as Associate Professor and Doctoral Supervisor at Southwestern University of Finance and Economics. From 2018 to 2025, he worked as Professor at Nanjing Audit University. He has served as visiting scholar at City University of Hong Kong, The Hong Kong Polytechnic University, and the Institute of Statistical Mathematics in Japan on multiple occasions. In 2022, he was selected as a Young and Middle-aged Academic Leader under Jiangsu Province's "Qinglan Project" for universities.
Research Interests
His current research interests include statistical reinforcement learning, graph deep learning, and federated learning. He has served as Principal Investigator for 4 National Natural Science Foundation of China (NSFC) projects and participated in 1 NSFC Key Program as sub-project leader. Over the past 10 years, he has published more than 20 academic papers in the fields of statistics and artificial intelligence, including publications in the top-tier statistics journal "Annals of Statistics" and CCF-A category AI journals/conferences such as "JMLR," "NeurIPS," and "IJCAI." Our focus lies at the intersection of statistics and artificial intelligence, with research philosophy guided by: cognitive science as inspiration, data-driven thinking as guidance, and mathematical foundations as support.
Contact Info:
Email: kenan716@ mail.ustc.edu.cn
Representative Publications
Selected SCI/SSCI Papers(*corresponding author):
1. Yibo Deng , Xin He , and Shaogao Lv*. (2024). Efficient learning nonparametric directed acyclic graph with statistical guarantee. Statistica Sinica. Online first.
2. Xin He, Junhui Wang and Shaogao Lv. (2021). Efficient kernel-based variable selection with sparsistency. Statistica Sinica. 31, 2123-2151.
3. Xin He, Shaogao Lv* and Junhui Wang.(2020). Variable selection for classification with derivative-induced regularization. Statistica Sinica. 30, 2075-2103.
4. Shaogao Lv∗, Zengyan Fan, Heng Lian, Taiji Suzuki , Kenji Fukumizu. (2020). A reproducing kernel Hilbert space approach to high dimensional partially varying coefficient model. Computational Statistics and Data Analysis, (152), 107039.
5. Heng Lian, Kaifeng Zhao and Shaogao Lv. (2019). Projected spline estimation of the nonparametric function in high-dimensional partially linear models for massive data. Annals of Statistics, (47), 2922-2949.
6. Shaogao Lv, Huazhen Lin*, Fanyin Zhou and Jian Huang. (2018). Oracle inequalities for high-dimensional additive Cox model. Scandinavian Journal of Statistics. (45), 900-922.
7. Shaogao Lv, Huazhen Lin*, Heng Lian and Jian Huang. (2018). On sign consistency of Lasso for high-dimensional Cox model. Journal of Multivariate Analysis, (167), 79-96.
8. Huazhen Lin, Lixian Pan and Shaogao Lv. (2018). Semiparametric efficient estimate of the generalized additive model with unknown link and variance. Journal of Econometrics, (202), 230-244.
9. Shaogao Lv, Huazhen Lin*, Heng Lian and Jian Huang. (2018). Oracle inequalities for sparse additive quantile regression in reproducing kernel Hilbert space. Annals of Statistics, (46), 781-813.
10. Xin He, Junhui Wang and Shaogao Lv*. (2018). Gradient-induced model-free variable selection with composite Quantile Regression. Statistica Sinica. (28), 1521-1538.
11. Shaogao Lv, Xin He and Junhui Wang*. (2017). A unified penalized method for sparse additive quantile models: a RKHS approach. Annals of the Institute of Statistical Mathematics, 69, 897-923.
12. Shiyu Liu, Wei Shi, Zenglin Xu, Shaogao Lv*, Yehong Zhang, Hui Wang.(2024). Meta-learning via PAC-Bayesian with data-dependent prior: generalization bounds from local entropy. The 32nd International Joint Conference on Artificial Intelligence (IJCAI 2024 ).
13. Shaogao Lv, Xin He* and Junhui Wang. (2023). Minimax kernel-based estimation for partially linear functional models. Journal of Machine Learning Research. (55):1−38.
14. Shiyu Liu, Shaogao Lv*, Linsen Wei and Ming Li. (2023). Stability and generalization of ℓp regularized stochastic learning for GCN. The 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023 ).
15. Xingcai Zhou, Le Chang, Pengfei Xu and Shaogao Lv*. (2022). Communication-efficient and Byzantine-robust distributed learning with statistical guarantee. Pattern Recognition. 137, 109312.
16. Shaogao Lv* and Heng Lian. (2022). Debiased distributed learning for sparse partial linear models in high dimensions. Journal of Machine Learning Research.23:1-32.
17. Shaogao Lv, Linsen Wei, Jiankun Liu and Yong Liu*. (2021). Improved learning rates of a functional Lasso-type SVM with sparse multi-kernel representation. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia.
18. Shaogao Lv, LinSen Wei, Zenglin Xu*, Qian Zhang. (2021). Improved inference for imputed based semi-supervised learning under misspeficed setting. IEEE Transaction Neural Network and Learning Systems. Doi: 10.1109/TNNLS.2021.3077312.
19. Guo Niu, Zhengming Ma* and Shaogao Lv. (2017). Ensemble multiple-kernel based manifold regularization. Neural processing Letter, 45, 539-552.
20. Lei Yang, Shaogao Lv and Junhui Wang. (2016). Model-free variable selection in reproducing kernel Hilbert space. Journal of Machine Learning Research, 17, 1-24.
21. Yunlong Feng, Shaogao Lv*, Hanyuan Han, Johan A.K. Suykens. (2016). Kernelized elastic net regularization: generalization bounds and sparse recovery. Neural Computation, 28, 525-562.
22. Shaogao Lv*. (2015). Refined generalization bounds of gradient learning over reproducing kernel Hilbert spaces. Neural Computation, (27), 1294-1320.
23. Shaogao Lv* and Fanyin Zhou. (2015). Optimal learning rates of L^p-type multiple kernel learning under general conditions. Information Science, (10) 255-268.
