Hongzhi Tong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Hongzhi Tong has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
Di-Rong Chen
Department of Mathematics and LMIB, Beijing University of Aeronautics and Astronautics , Beijing, P.R. China
7 shared publicationsFenghong Yang
School of Statistics and Mathematics, Central University of Finance and Economics , Beijing, P.R. China
6 shared publications- Michael KwokPo Ng
Department of Mathematics, Hong Kong Baptist University, Kowloon Tong, Hong Kong
3 shared publications - Di-Rong Chen
School of Mathematical Science, Beihang University, Beijing, China
2 shared publications - FengHong YANG1 shared publication
- Jiajing Gao
School of Statistics, University of International Business and Economics, Beijing 100029, P.R.C.
1 shared publication
Latest Publications
- 30 September 2026
- Published by Elsevier in Journal of Mathematical Analysis and Applications
- Vol. 567 (1)
Distributed gradient descent algorithm for robust kernel-based regression
- 30 September 2026
- Published by Elsevier in Journal of Mathematical Analysis and Applications
- Vol. 567 (1)
Distributed gradient descent algorithm for robust kernel-based regression
- 16 May 2026
- Published by Elsevier in Applied and Computational Harmonic Analysis
- Vol. 85
Learning theory of regularized Huber regression
- 16 May 2026
- Published by Elsevier in Applied and Computational Harmonic Analysis
- Vol. 85
Learning theory of regularized Huber regression
- 22 November 2024
- Published by World Scientific Pub Co Pte Ltd in Analysis and Applications
- Vol. 23 (05) , 867-885
Convergence rates of regularized Huber regression under weak moment conditions
Huber regression plays a critical role in robust learning owing to its robustness to outliers and heavy-tailed noises. In this paper, we investigate the theoretical foundation of an Ivanov regularized Huber regression within a Reproducing Kernel Hilbert Space (RKHS) framework. By imposing a weak moment condition on the conditional distribution, we show that Huber regression estimator with the scale parameter adapted to sample size can learn the underlying regression function very well. Specifically, we establish the explicit convergence rates of the prediction error even when the regression function is outside the associated RKHS. Our statistical analysis could greatly improve the understanding of the learning behavior of Huber regression in the absence of light-tailed assumption on the conditional distribution.
- 22 November 2024
- Published by World Scientific Pub Co Pte Ltd in Analysis and Applications
- Vol. 23 (05) , 867-885
Convergence rates of regularized Huber regression under weak moment conditions
Huber regression plays a critical role in robust learning owing to its robustness to outliers and heavy-tailed noises. In this paper, we investigate the theoretical foundation of an Ivanov regularized Huber regression within a Reproducing Kernel Hilbert Space (RKHS) framework. By imposing a weak moment condition on the conditional distribution, we show that Huber regression estimator with the scale parameter adapted to sample size can learn the underlying regression function very well. Specifically, we establish the explicit convergence rates of the prediction error even when the regression function is outside the associated RKHS. Our statistical analysis could greatly improve the understanding of the learning behavior of Huber regression in the absence of light-tailed assumption on the conditional distribution.
- 28 October 2024
- Published by Elsevier in Journal of Computational and Applied Mathematics
- Vol. 458
Least squares regression under weak moment conditions
- 28 October 2024
- Published by Elsevier in Journal of Computational and Applied Mathematics
- Vol. 458
Least squares regression under weak moment conditions
- 25 December 2021
- Published by Springer Nature in Acta Mathematica Sinica, English Series
- Vol. 38 (4) , 777-796
Non-asymptotic Error Bound for Optimal Prediction of Function-on-Function Regression by RKHS Approach
- 25 December 2021
- Published by Springer Nature in Acta Mathematica Sinica, English Series
- Vol. 38 (4) , 777-796
Non-asymptotic Error Bound for Optimal Prediction of Function-on-Function Regression by RKHS Approach
- 23 December 2021
- Published by IOP Publishing in Inverse Problems
- Vol. 38 (2) , 025002
Distributed least squares prediction for functional linear regression*
To cope with the challenges of memory bottleneck and algorithmic scalability when massive data sets are involved, we propose a distributed least squares procedure in the framework of functional linear model and reproducing kernel Hilbert space. This approach divides the big data set into multiple subsets, applies regularized least squares regression on each of them, and then averages the individual outputs as a final prediction. We establish the non-asymptotic prediction error bounds for the proposed learning strategy under some regularity conditions. When the target function only has weak regularity, we also introduce some unlabelled data to construct a semi-supervised approach to enlarge the number of the partitioned subsets. Results in present paper provide a theoretical guarantee that the distributed algorithm can achieve the optimal rate of convergence while allowing the whole data set to be partitioned into a large number of subsets for parallel processing.
- 23 December 2021
- Published by IOP Publishing in Inverse Problems
- Vol. 38 (2) , 025002
Distributed least squares prediction for functional linear regression*
To cope with the challenges of memory bottleneck and algorithmic scalability when massive data sets are involved, we propose a distributed least squares procedure in the framework of functional linear model and reproducing kernel Hilbert space. This approach divides the big data set into multiple subsets, applies regularized least squares regression on each of them, and then averages the individual outputs as a final prediction. We establish the non-asymptotic prediction error bounds for the proposed learning strategy under some regularity conditions. When the target function only has weak regularity, we also introduce some unlabelled data to construct a semi-supervised approach to enlarge the number of the partitioned subsets. Results in present paper provide a theoretical guarantee that the distributed algorithm can achieve the optimal rate of convergence while allowing the whole data set to be partitioned into a large number of subsets for parallel processing.
- 1 October 2020
- Published by MIT Press in Neural Computation
- Vol. 32 (10) , 1980-1997
Analysis of Regression Algorithms with Unbounded Sampling
In this letter, we study a class of the regularized regression algorithms when the sampling process is unbounded. By choosing different loss functions, the learning algorithms can include a wide range of commonly used algorithms for regression. Unlike the prior work on theoretical analysis of unbounded sampling, no constraint on the output variables is specified in our setting. By an elegant error analysis, we prove consistency and finite sample bounds on the excess risk of the proposed algorithms under regular conditions. In this letter, we study a class of the regularized regression algorithms when the sampling process is unbounded. By choosing different loss functions, the learning algorithms can include a wide range of commonly used algorithms for regression. Unlike the prior work on theoretical analysis of unbounded sampling, no constraint on the output variables is specified in our setting. By an elegant error analysis, we prove consistency and finite sample bounds on the excess risk of the proposed algorithms under regular conditions. In this letter, we study a class of the regularized regression algorithms when the sampling process is unbounded. By choosing different loss functions, the learning algorithms can include a wide range of commonly used algorithms for regression. Unlike the prior work on theoretical analysis of unbounded sampling, no constraint on the output variables is specified in our setting. By an elegant error analysis, we prove consistency and finite sample bounds on the excess risk of the proposed algorithms under regular conditions.
- 1 October 2020
- Published by MIT Press in Neural Computation
- Vol. 32 (10) , 1980-1997
Analysis of Regression Algorithms with Unbounded Sampling
In this letter, we study a class of the regularized regression algorithms when the sampling process is unbounded. By choosing different loss functions, the learning algorithms can include a wide range of commonly used algorithms for regression. Unlike the prior work on theoretical analysis of unbounded sampling, no constraint on the output variables is specified in our setting. By an elegant error analysis, we prove consistency and finite sample bounds on the excess risk of the proposed algorithms under regular conditions. In this letter, we study a class of the regularized regression algorithms when the sampling process is unbounded. By choosing different loss functions, the learning algorithms can include a wide range of commonly used algorithms for regression. Unlike the prior work on theoretical analysis of unbounded sampling, no constraint on the output variables is specified in our setting. By an elegant error analysis, we prove consistency and finite sample bounds on the excess risk of the proposed algorithms under regular conditions. In this letter, we study a class of the regularized regression algorithms when the sampling process is unbounded. By choosing different loss functions, the learning algorithms can include a wide range of commonly used algorithms for regression. Unlike the prior work on theoretical analysis of unbounded sampling, no constraint on the output variables is specified in our setting. By an elegant error analysis, we prove consistency and finite sample bounds on the excess risk of the proposed algorithms under regular conditions.
- 6 February 2018
- Published by Taylor & Francis in Applicable Analysis
- Vol. 98 (9) , 1626-1635
Support vector machines regression with unbounded sampling
Uniform boundedness of output variables is a standard assumption in most theoretical analysis of regression algorithms. This standard assumption has recently been weaken to a moment hypothesis in least square regression (LSR) setting. Although there has been a large literature on error analysis for LSR under the moment hypothesis, very little is known about the statistical properties of support vector machines regression with unbounded sampling. In this paper, we fill the gap in the literature. Without any restriction on the boundedness of the output sampling, we establish an ad hoc convergence analysis for support vector machines regression under very mild conditions.
- 6 February 2018
- Published by Taylor & Francis in Applicable Analysis
- Vol. 98 (9) , 1626-1635
Support vector machines regression with unbounded sampling
Uniform boundedness of output variables is a standard assumption in most theoretical analysis of regression algorithms. This standard assumption has recently been weaken to a moment hypothesis in least square regression (LSR) setting. Although there has been a large literature on error analysis for LSR under the moment hypothesis, very little is known about the statistical properties of support vector machines regression with unbounded sampling. In this paper, we fill the gap in the literature. Without any restriction on the boundedness of the output sampling, we establish an ad hoc convergence analysis for support vector machines regression under very mild conditions.
- 1 January 2018
- Published by International Press of Boston in Communications in Mathematical Sciences
- Vol. 16 (5) , 1347-1360
Regularized semi-supervised least squares regression with dependent samples
International Press of Boston - publishers of scholarly mathematical and scientific journals and books
- 1 January 2018
- Published by International Press of Boston in Communications in Mathematical Sciences
- Vol. 16 (5) , 1347-1360
Regularized semi-supervised least squares regression with dependent samples
International Press of Boston - publishers of scholarly mathematical and scientific journals and books
- 1 January 2016
- Published by MIT Press in Neural Computation
- Vol. 28 (1) , 71-88
A Note on Support Vector Machines with Polynomial Kernels
We present a better theoretical foundation of support vector machines with polynomial kernels. The sample error is estimated under Tsybakov’s noise assumption. In bounding the approximation error, we take advantage of a geometric noise assumption that was introduced to analyze gaussian kernels. Compared with the previous literature, the error analysis in this note does not require any regularity of the marginal distribution or smoothness of Bayes’ rule. We thus establish the learning rates for polynomial kernels for a wide class of distributions.
- 1 January 2016
- Published by MIT Press in Neural Computation
- Vol. 28 (1) , 71-88
A Note on Support Vector Machines with Polynomial Kernels
We present a better theoretical foundation of support vector machines with polynomial kernels. The sample error is estimated under Tsybakov’s noise assumption. In bounding the approximation error, we take advantage of a geometric noise assumption that was introduced to analyze gaussian kernels. Compared with the previous literature, the error analysis in this note does not require any regularity of the marginal distribution or smoothness of Bayes’ rule. We thus establish the learning rates for polynomial kernels for a wide class of distributions.