Center for Statistical Science
Tsinghua University Weiqing Building 209a
Beijing China 100084
Email: qianlin "at" mail | tsinghua | edu | cn
Educations
Ph.D. (2010) in Mathematics, Massachusetts Institute of Technology
Research Interests
Dimension Reduction, Kernel Methods, Deep Learning
Publications
Neural Networks and Kernel Regression
The phase diagram of kernel interpolation in large dimensions
On the asymptotic learning curves of kernel ridge regression under power-law decay
The Optimality of Kernel Classifiers in Sobolev Space
Generalization Error Curves for Analytic Spectral Algorithms under Power-law Decay
Optimal Rates of Kernel Ridge Regression under Source Condition in Large Dimensions
Yicheng Li, Haobo Zhang and Qian Lin*, "On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law Decay", NeurIPS2023
Weihao Lu, Haobo Zhang, Yicheng Li, Manyun Xu, and Qian Lin*, "Optimal rate of kernel regression in large dimensions", arXiv
Yicheng Li, Zixiong Yu, Guhan Chen and Qian Lin*, "On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains"( originally named "Statistical optimality of deep wide neural networks"), arXiv, Journal of Machine Learning Research, 2024
Haobo Zhang, Yicheng Li and Qian Lin*, "On the optimality of misspecified spectral algorithms", arXiv, Journal of Machine Learning Research, 2024
Haobo Zhang, Yicheng Li, Weihao Lu and Qian Lin*, "On the optimality of misspecified kernel ridge regression",ICML2023
Yicheng Li, Haobo Zhang and Qian Lin*, "Kernel interpolation generalizes poorly", arXiv , Biometrika ( to appear)
Jianfa Lai, Manyun Xu, Rui Chen and Qian Lin*, "Generalization ability of wide neural network on R", arXiv
Yicheng Li, Haobo Zhang and Qian Lin*, "On the Saturation effects of kernel ridge regression ", ICLR 2023
Sufficient Dimension Reduction
Qian Lin, "Sparse sliced average variance estimation"
Dongming Huang, Songtao Tian, Qian Lin*, "Sliced inverse regression with large structural dimension", arXiv
Qian Lin, X. Li, D. Huang and J. S. Liu. "On Optimality of Sliced Inverse Regression in High Dimensions", Annals of Statistics. 2021. Volume 49, Number 1 (2021): 1-20;
Qian Lin, Z. Zhao and J. S. Liu. "Sparse Sliced Inverse Regression via Lasso", Journal of the American Statistical Association. Volume 114 , Issue 528 (2019): 1726-1739;
Qian Lin, Z. Zhao and J. S. Liu. "On Consistency and Sparsity of Sliced Inverse Regression in High Dimensions," Annals of Statistics. Volume 46, Number 2 (2018): 580-610. arXiv
M. Neykov, Qian Lin and J. S. Liu. "Signed Support Recovery for Single Index Models in High Dimensions", Annals of Mathematical Sciences and Applications Vol. 1 No. 2 (2016): 379-426 arXiv
Qian Lin, Z. Zhao and J. S. Liu. "Global Testing under the Sparse Alternatives for Single Index Models", Festschrift in Honor of R. Dennis Cook, 2021, (Book Chapter) ;
Qian Lin, Y. Li and J. S. Liu. "Inverse Modeling: A strategy to cope with nonlinearity, Handbook of Big Data Analytics", Springer ; In Press, 2016, (Book Chapter) ;
Causal Inference
X. Li, P. Ding , Qian Lin, D. Yang and J. S. Liu. "Randomization-based inference for peer effects", Journal of the American Statistical Association. Volume 114 , Issue 528 (2019): 1651-1664;
Others:
Qian Lin and M. Wang. "Isogeny orbits in a family of abelian varieties", Acta Arithmetica 170(2015), 161-173 , arxiv:1403.3976
Roman Bezrukavnikov and Qian Lin. "Highest weight modules at the critical level and noncommutative Springer resolution", Algebraic Groups and Quantum Groups, Contemp. Math 565 (2012): 15-27 , arxiv:1108.1906
Qian Lin, Z. Liu and Y. Sheng. "Quadratic Deformations of Lie-Poisson Structures", Letters in Mathematical Physics 83 (2008): 217-229, arxiv:0707.2867