Published Papers

(Supervised students are underlined.)

• Truncated kernel stochastic gradient descent on spheres (with J. Bai), Mathematics of Computation, published online (2025), 72pp.
• Single-step neural operator solver for semilinear evolution equations (with Z. Lei and X. Wang), Chinese Annals of Mathematics, Series B 46(2025), 321-340.
• Nyström subsampling for functional linear regression (with J. Fan and J. Liu), Journal of Approximation Theory 310(2025), 106176 (25pp).
• A decentralized framework for kernel PCA with projection consensus constraints (with F. He, R. Yang and X. Huang), IEEE Transactions on Pattern Analysis and Machine Intelligence 47(2025), 3908-3921.
• Distributed learning with discretely observed functional data (with J. Liu), Inverse Problems 41(2025), 045006 (45pp).
• Solving PDEs on spheres with physics-informed convolutional neural networks (with G. Lei, Z. Lei, C. Zeng and D.-X. Zhou), Applied and Computational Harmonic Analysis 74(2025), 101719 (40pp).
• Pairwise ranking with Gaussian kernel (with G. Lei), Advances in Computational Mathematics 50(2024), 1-56.
• Iterative kernel regression with preconditioning (with Z. Zhang), Analysis and Applications 22(2024), 1095-1131.
• Spectral algorithms for functional linear regression (with J. Fan and Z.-C. Guo), Communications on Pure and Applied Analysis 23(2024), 895-915.
• Optimality of robust online learning (with Z.-C. Guo and A. Christmann), Foundations of Computational Mathematics 24(2024), 1455-1483.
• Optimal gradient tracking for decentralized optimization (with Z. Song, S. Pu and M. Yan), Mathematical Programming 207(2024), 1-53.
• Statistical optimality of divide and conquer kernel-based functional linear regression (with J. Liu), Journal of Machine Learning Research 25(2024), 1-56.
• Classification with deep neural networks and logistic loss (with Z. Zhang and D.-X. Zhou), Journal of Machine Learning Research 25(2024), 1-117.
• Provably accelerated decentralized gradient methods over unbalanced directed graphs (with Z. Song, S. Pu and M. Yan), SIAM Journal on Optimization 34(2024), 1131-1156.
• Efficient kernel canonical correlation analysis using Nyström approximation (with Q. Fang, M. Xu and D.-X. Zhou), Inverse Problems 40(2024), 045007 (28pp).
• Coefficient-based regularized distribution regression (with Y. Mao and Z.-C. Guo), Journal of Approximation Theory 297(2024), 105995 (37pp).
• Global search and analysis for the nonconvex two-level l1 Penalty (with F. He, M. He and X. Huang), IEEE Transactions on Neural Networks and Learning Systems 35(2024), 3886-3899.
• Capacity dependent analysis for functional online learning algorithms (with X. Guo and Z.-C. Guo), Applied and Computational Harmonic Analysis 67(2023), 101567 (30pp).
• Learning with asymmetric kernels: least squares and feature interpretation (with M. He, F. He, X. Huang and JAK. Suykens), IEEE Transactions on Pattern Analysis and Machine Intelligence 45(2023), 10044-10054.
• Distributed spectral pairwise ranking algorithms (with Z.-C. Guo and T. Hu), Inverse Problems 39(2023), 025003 (21pp).
• Communication-efficient topologies for decentralized learning with O(1) consensus rate (with Z. Song et al.), NeurIPS 2022.
• Solving parametric partial differential equations with deep rectified quadratic unit neural networks (with Z. Lei and C. Zeng), Journal of Scientific Computing 93(2022), 1-31.
• Compressed gradient tracking for decentralized optimization over general directed networks (with Z. Song, S. Pu and M. Yan), IEEE Transactions on Signal Processing 70(2022), 1775-1787.
• Regularized regression problem in hyper-RKHS for learning kernels (with F. Liu, X. Huang, J. Yang and JAK. Suykens), Journal of Machine Learning Research 22(2021), 1–38.
• Analysis of Regularized Least-Squares in Reproducing Kernel Krĕın Spaces (with F. Liu, X. Huang, J. Yang and JAK. Suykens), Machine Learning 110(2021), 1145–1173.
• Fast algorithms for robust principal component analysis with an upper bound on the rank (with N. Sha and M. Yan), Inverse Problems and Imaging 15(2021), 109-128.
• Realizing data features by deep nets (with Z.-C. Guo and S.-B. Lin), IEEE Transactions on Neural Networks and Learning Systems 31(2020), 4036-4048.
• A double-variational Bayesian framework in random Fourier features for indefinite kernels (with F. Liu, X. Huang, J. Yang and JAK. Suykens), IEEE Transactions on Neural Networks and Learning Systems 31(2020),2965-2979.
• Sparse SIR: optimal rates and adaptive estimation (with K. Tan and Z. Yu), Annals of Statistics 48(2020), 64-85.
• Sparse kernel regression with coefficient-based lq-regularization (with X. Huang, Y. Feng and JAK. Suykens), Journal of Machine Learning Research 20(2019), 1-44.
• Fast and strong convergence of online learning algorithms (with Z.-C. Guo), Advances in Computational Mathematics 45(2019), 2745-2770.
• Distributed learning with indefinite kernels, Analysis and Applications 17(2019), 947-975.
• Optimal rates for coefficient-based regularized regression (with Z.-C. Guo), Applied and Computational Harmonic Analysis 47(2019), 662-701.
• An RKHS approach to estimate individualized treatment rules based on functional predictors (with J. Fan and F. Lv), Mathematical Foundations of Computing 2(2019), 169-181.
• Nyström subsampling method for coefficient-based regularized regression (with L. Ma and Z. Wu), Inverse Problems 35(2019), 075002 (40pp).
• Robust mixed one-bit compressive sensing (with X. Huang, Y. Huang, Y. Huang, F. He, A. Maier and M. Yan), Signal Processing 162(2019), 161-168.
• Distributed learning with multi-penalty regularization (with Z.-C. Guo and S.-B. Lin), Applied and Computational Harmonic Analysis 46(2019), 478-499.
• Gradient descent for robust kernel-based regression (with Z.-C. Guo and T. Hu), Inverse Problems 34(2018), 065009 (29pp).
• Convergence of unregularized online learning algorithms (with Y. Lei and Z.-C. Guo), Journal of Machine Learning Research 18(2018), 1-33.
• Pinball loss minimization for one-bit compressive sensing (with X. Huang, M. Yan and JAK. Suykens), Neurocomputing 314(2018), 275-283.
• Learning theory of distributed regression with bias corrected regularization kernel network (with Z.-C. Guo and Q. Wu), Journal of Machine Learning Research 18(2017), 1-25.
• Solution path for pin-SVM classifiers with positive and negative tau value (with X. Huang and JAK Suykens), IEEE Transactions on Neural Networks and Learning Systems 28(2017), 1584-1593.
• Learning rates for regularized least squares ranking algorithm (with Y. Zhao and J. Fan), Analysis and Applications 15(2017), 815-836.
• Nonconvex sorted l1 minimization for sparse approximation (with X. Huang and M. Yan), Journal of the Operations Research Society of China 3(2015), 207-229.
• Learning with the maximum correntropy criterion induced losses for regression (with Y. Feng, X. Huang, Y. Yang and JAK. Suykens)，Journal of Machine Learning Research 16(2015), 993-1034.
• Two-level l1 minimization for compressed sensing (with X. Huang, Y. Liu, S. Van Huffel and JAK. Suykens), Signal Processing 108(2015), 205204, 459-475.
• Sequential minimal optimization for SVM with pinball loss (with X. Huang and JAK. Suykens), Neurocomputing 149(2015), 1596-1603.
• Ramp loss linear programming support vector machine (with X. Huang and JAK. Suykens), Journal of Machine Learning Research 15(2014), 2185-2211.
• Support vector machine classifier with pinball loss (with X. Huang and JAK. Suykens), IEEE Transactions on Pattern Analysis and Machine Intelligence 36(2014), 984-997.
• Quantile regression with l1-regularization and Gaussian kernels (with X. Huang, Z. Tian and JAK. Suykens)，Advances in Computational Mathematics 40(2014), 517-551.
• Asymmetric ν-tube support vector regression (with X. Huang, K. Pelckmansand and JAK. Suykens), Computational Statistics & Data Analysis 77(2014), 371-382.
• Asymmetric least squares support vector machine classifiers (with X. Huang and JAK. Suykens), Computational Statistics & Data Analysis 70(2014), 395-405.
• Learning with coefficient-based regularization and l1-penalty (with Z.-C. Guo), Advances in Computational Mathematics 39(2013), 493-510.
• Learning theory estimates for coefficient-based regularized regression, Applied and Computational Harmonic Analysis 34(2013), 252-265.
• Non-uniform randomized sampling for multivariate approximation by high order Parzen windows (with X.-J. Zhou and D.-X. Zhou), Canadian Mathematical Bulletin 54(2011), 566-576.
• Classification with non-iid sampling (with Z.-C. Guo), Mathematical and Computer Modelling 54(2011), 1347-1364.
• Concentration estimates for learning with l1-regularizer and data dependent hypothesis spaces (with Y. Feng and D.-X. Zhou), Applied and Computational Harmonic Analysis 31(2011), 286-302.
• Normal estimation on manifolds by gradient learning (with D.-X. Zhou), Numerical Linear Algebra with Applications 18(2011), 249-259.
• Learning theory viewpoint of approximation by positive linear operators (with S. Lv), Computers and Mathematics with Applications 60(2010), 3177-3186.
• Hermite learning with gradient data (with X. Guo and D.-X. Zhou), Journal of Computational and Applied Mathematics 233(2010), 3046-3059.