Yicheng Li& and Qian Lin*.    "Diagonal over-parameterization in RKHS as an adaptive feature model: generalization and adaptivity",   arXiv 2501.08679

Yicheng Li& and Qian Lin*.    "Improving adaptivity via over-parameterization in sequence models", NeurIPS2024    arXiv 2409.00894

Haobo Zhang&, Jianfa Lai&, Yicheng Li&,  Qian Lin, and Jun S. Liu*.    "Towards a statistical understanding of neural networks: beyond the neural tangent kernel theories",    arXiv 2421.18756

Guhan Chen&, Yicheng Li&, and Qian Lin*.    "On the impacts of the random initialization in the neural tangent kernel theory,",    NeurIPS 2024, arXiv 2410.05626

Weihao Lu&, Haobo Zhang&, Yicheng Li& and Qian Lin*.    "On the saturation effects of spectral algorithms in large dimensions",    NeurIPS2024

Weihao Lu&, Jialing Ding&, Haobo Zhang and Qian Lin*.    "On the Pinsker bound of inner product kernel regression in large dimensions",    arXiv 2409.00915

Jianfa Lai&, Zhifan Li&, Dongming Huang and Qian Lin*.    "The optimality of kernel classifiers in Sobolev space",    ICLR 2024

Yicheng Li&, Haobo Zhang&  and Qian Lin*.    "On the asymptotic learning curves of kernel ridge regression under power-law decay",    NeurIPS2023

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*.    "On the saturation effects of kernel ridge regression ",    ICLR 2023

Yicheng Li&, Weiye Gan, Zuoqiang Shi,  and Qian Lin*.    "Generalization error curves for analytic spectral algorithms under power-law Decay",    arXiv 2401.01599

Haobo Zhang&, Weihao Lu&, Yicheng Li&, and Qian Lin*.    "Optimal rates of kernel ridge regression under source condition in large dimensions",   ournal of Machine Learning Research arXiv 2401.01270

Haobo Zhang&, Weihao Lu& and Qian Lin*.    "The phase diagram of kernel interpolation in large dimensions",    arXiv 2404.12597

Weihao Lu&, Haobo Zhang&, Yicheng Li&, Manyun Xu&, and Qian Lin*.    "Optimal rate of kernel regression in large dimensions",    arXiv 2309.04268

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"    Journal of Machine Learning Research, 25(82):1-47,2024    (originally named "Statistical optimality of deep wide neural networks"),    arXiv 2305.02657 

Haobo Zhang&, Yicheng Li& and Qian Lin*.    "On the optimality of misspecified spectral algorithms",    Journal of Machine Learning Research, 25(188):1−50, 2024    arXiv 2303.14942

Yicheng Li&, Haobo Zhang& and Qian Lin*.    "Kernel interpolation generalizes poorly",    Biometrika, Volume 111, Issue 2, June 2024.    Pages 715–722,    arXiv 2303.15809

Jianfa Lai&, Manyun Xu&, Rui Chen& and Qian Lin*.    "Generalization ability of wide neural network on R",    arXiv 2302.05933

Dongming Huang, Songtao Tian&, Qian Lin*.    "On the structure dimension of sliced inverse regression",    arXiv 2305.04340

Qian Lin, Xinran Li, Dongming Huang and Jun S. Liu.    "On optimality  of sliced inverse regression in high dimensions",    Annals of Statistics, 2021. Volume 49, Number 1 (2021): 1-20

Qian Lin, Zhigen Zhao and Jun S. Liu.    "Sparse sliced inverse regression via Lasso",    Journal of the American Statistical Association, Volume 114 , Issue 528 (2019): 1726-1739

Qian Lin,  Zhigen Zhao and Jun S. Liu.    "On consistency and sparsity of sliced inverse regression in high dimensions,"    Annals of Statistics, Volume 46, Number 2 (2018): 580-610     arXiv   

Matey Neykov, Qian Lin and Jun 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, Zhigen Zhao and Jun S. Liu.    "Global testing under the sparse alternatives for single index models",    Festschrift in Honor of R. Dennis Cook, 2021, (Book Chapter) ;

Qian Lin, Yang Li and Jun S. Liu.    "Inverse Modeling: A strategy to cope with nonlinearity,  Handbook of Big Data Analytics", Springer ; In Press, 2016,   (Book Chapter) 

Xinran Li, Peng Ding , Qian Lin, Dawei Yang and Jun S. Liu.    "Randomization-based inference for peer effects",    Journal of the American Statistical Association,  Volume 114 , Issue 528 (2019): 1651-1664