Huiming Zhang
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
Huiming Zhang has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
Bo Li
School of Mathematics and Statistics, Central China Normal University, Wuhan, China
3 shared publications- Bo Li
School of Mathematics and Statistics Central China Normal University 430079 Wuhan China
2 shared publications - Haoyu Wei
Department of Statistics, North Carolina State University, Raleigh, NC 27695, USA
2 shared publications - Haoyu Wei
Department of Economics University of California San Diego 9500 Gilman Dr 92093 La Jolla CA
2 shared publications - Jinzhu Jia
Department of Biostatistics, School of Public Health, Peking University, Beijing, China
2 shared publications Shuang Song
Center for Statistical Science, Tsinghua University, Beijing, China
2 shared publications
Latest Publications
- 3 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 71 (3) , 1885-1892
Distributed Stochastic Optimization Under Heavy-Tailed Noises
This paper studies the distributed optimization problem in the presence of heavy-tailed gradient noises. Here, a heavy-tailed noise $\xi$ does not necessarily adhere to the bounded variance assumption, i.e., $ {\mathbb {E}}[\Vert \xi \Vert ^{2}]\leq \nu ^{2}$ for some positive constant $\nu$. Instead, it satisfies a more general condition $ {\mathbb {E}}[\Vert \xi \Vert ^\delta ]\leq \nu ^\delta$ for some $1< \delta \leq 2$. The commonly-used bounded variance assumption is a special case of the considered noise assumption. While several distributed optimization algorithms have been proposed for scenarios involving heavy-tailed noise, these algorithms need a centralized server in the network which collects the information of all clients. Different from these algorithms, this paper considers a scenario where there is no centralized server and the agents can only exchange information with neighbors within a communication graph. A distributed method combining gradient clipping and distributed stochastic gradient projection is proposed. It is proven that when the gradient descent step-size and the gradient clipping step-size meet certain conditions, the state of each agent converges to an optimal solution of the distributed optimization problem with probability 1. The simulation results validate the algorithm.
- 3 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 71 (3) , 1885-1892
Distributed Stochastic Optimization Under Heavy-Tailed Noises
This paper studies the distributed optimization problem in the presence of heavy-tailed gradient noises. Here, a heavy-tailed noise $\xi$ does not necessarily adhere to the bounded variance assumption, i.e., $ {\mathbb {E}}[\Vert \xi \Vert ^{2}]\leq \nu ^{2}$ for some positive constant $\nu$. Instead, it satisfies a more general condition $ {\mathbb {E}}[\Vert \xi \Vert ^\delta ]\leq \nu ^\delta$ for some $1< \delta \leq 2$. The commonly-used bounded variance assumption is a special case of the considered noise assumption. While several distributed optimization algorithms have been proposed for scenarios involving heavy-tailed noise, these algorithms need a centralized server in the network which collects the information of all clients. Different from these algorithms, this paper considers a scenario where there is no centralized server and the agents can only exchange information with neighbors within a communication graph. A distributed method combining gradient clipping and distributed stochastic gradient projection is proposed. It is proven that when the gradient descent step-size and the gradient clipping step-size meet certain conditions, the state of each agent converges to an optimal solution of the distributed optimization problem with probability 1. The simulation results validate the algorithm.
- 3 August 2025
- Published by Springer Nature in Communications in Mathematics and Statistics
- p. 1-18
Directional FDR Control for Sub-Gaussian Sparse GLMs
- 3 August 2025
- Published by Springer Nature in Communications in Mathematics and Statistics
- p. 1-18
Directional FDR Control for Sub-Gaussian Sparse GLMs
- Open Access
- 14 July 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (14) , 2267
Editorial: New Advances in High-Dimensional and Non-Asymptotic Statistics
This editorial paper reviews the Special Issue “New Advances in High-Dimensional and Non-asymptotic Statistics” and summarizes the ten collected papers
- 14 July 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (14) , 2267
Open AccessEditorial: New Advances in High-Dimensional and Non-Asymptotic Statistics
This editorial paper reviews the Special Issue “New Advances in High-Dimensional and Non-asymptotic Statistics” and summarizes the ten collected papers
- Open Access
- 18 February 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (4) , 665
Selective Reviews of Bandit Problems in AI via a Statistical View
Reinforcement Learning (RL) is a widely researched area in artificial intelligence that focuses on teaching agents decision-making through interactions with their environment. A key subset includes multi-armed bandit (MAB) and stochastic continuum-armed bandit (SCAB) problems, which model sequential decision-making under uncertainty. This review outlines the foundational models and assumptions of bandit problems, explores non-asymptotic theoretical tools like concentration inequalities and minimax regret bounds, and compares frequentist and Bayesian algorithms for managing exploration–exploitation trade-offs. Additionally, we explore K-armed contextual bandits and SCAB, focusing on their methodologies and regret analyses. We also examine the connections between SCAB problems and functional data analysis. Finally, we highlight recent advances and ongoing challenges in the field.
- 18 February 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (4) , 665
Open AccessSelective Reviews of Bandit Problems in AI via a Statistical View
Reinforcement Learning (RL) is a widely researched area in artificial intelligence that focuses on teaching agents decision-making through interactions with their environment. A key subset includes multi-armed bandit (MAB) and stochastic continuum-armed bandit (SCAB) problems, which model sequential decision-making under uncertainty. This review outlines the foundational models and assumptions of bandit problems, explores non-asymptotic theoretical tools like concentration inequalities and minimax regret bounds, and compares frequentist and Bayesian algorithms for managing exploration–exploitation trade-offs. Additionally, we explore K-armed contextual bandits and SCAB, focusing on their methodologies and regret analyses. We also examine the connections between SCAB problems and functional data analysis. Finally, we highlight recent advances and ongoing challenges in the field.
- Open Access
High-dimensional Inference and FDR Control for Simulated Markov Random Fields
Identifying important features linked to a response variable is a fundamental task in various scientific domains. This article explores statistical inference for simulated Markov random fields in high-dimensional settings. We introduce a methodology based on Markov Chain Monte Carlo Maximum Likelihood Estimation (MCMC-MLE) with Elastic-net regularization. Under mild conditions on the MCMC method, our penalized MCMC-MLE method achieves $\ell_{1}$-consistency. We propose a decorrelated score test, establishing both its asymptotic normality and that of a one-step estimator, along with the associated confidence interval. Furthermore, we construct two false discovery rate control procedures via the asymptotic behaviors for both p-values and e-values. Comprehensive numerical simulations confirm the theoretical validity of the proposed methods.
Open AccessHigh-dimensional Inference and FDR Control for Simulated Markov Random Fields
Identifying important features linked to a response variable is a fundamental task in various scientific domains. This article explores statistical inference for simulated Markov random fields in high-dimensional settings. We introduce a methodology based on Markov Chain Monte Carlo Maximum Likelihood Estimation (MCMC-MLE) with Elastic-net regularization. Under mild conditions on the MCMC method, our penalized MCMC-MLE method achieves $\ell_{1}$-consistency. We propose a decorrelated score test, establishing both its asymptotic normality and that of a one-step estimator, along with the associated confidence interval. Furthermore, we construct two false discovery rate control procedures via the asymptotic behaviors for both p-values and e-values. Comprehensive numerical simulations confirm the theoretical validity of the proposed methods.
- Open Access
Distribution Estimation of Contaminated Data via DNN-based MoM-GANs
This paper studies the distribution estimation of contaminated data by the MoM-GAN method, which combines generative adversarial net (GAN) and median-of-mean (MoM) estimation. We use a deep neural network (DNN) with a ReLU activation function to model the generator and discriminator of the GAN. Theoretically, we derive a non-asymptotic error bound for the DNN-based MoM-GAN estimator measured by integral probability metrics with the $b$-smoothness H\"{o}lder class. The error bound decreases essentially as $n^{-b/p}\vee n^{-1/2}$, where $n$ and $p$ are the sample size and the dimension of input data. We give an algorithm for the MoM-GAN method and implement it through two real applications. The numerical results show that the MoM-GAN outperforms other competitive methods when dealing with contaminated data.Open AccessDistribution Estimation of Contaminated Data via DNN-based MoM-GANs
This paper studies the distribution estimation of contaminated data by the MoM-GAN method, which combines generative adversarial net (GAN) and median-of-mean (MoM) estimation. We use a deep neural network (DNN) with a ReLU activation function to model the generator and discriminator of the GAN. Theoretically, we derive a non-asymptotic error bound for the DNN-based MoM-GAN estimator measured by integral probability metrics with the $b$-smoothness H\"{o}lder class. The error bound decreases essentially as $n^{-b/p}\vee n^{-1/2}$, where $n$ and $p$ are the sample size and the dimension of input data. We give an algorithm for the MoM-GAN method and implement it through two real applications. The numerical results show that the MoM-GAN outperforms other competitive methods when dealing with contaminated data. Asymptotic normality and confidence region for Catoni's Z estimator
This paper studies the asymptotic property and confidence region of Catoni's Z estimator under the finite variance assumption. First, we investigate the CLT for Catoni's Z estimator with the asymptotically optimal variance, if the tuning parameter has order . Second, we propose the normal approximated confidence region of Catoni's Z estimator. The simulations show that the proposed 99% CLT‐based confidence regions are shorter than the existing non‐asymptotic confidence regions; mean squared errors of Catoni's Z estimators are typically smaller than sample means from heavy‐tailed data. Furthermore, the simulated coverage probabilities of the CLT‐based confidence region are close to the confidence levels when the sample size is moderately large. For 6‐year DOCVIS data (the number of doctor visits) in the German health care demand dataset, our CLT‐based confidence regions are tighter than non‐asymptotic confidence regions.
Asymptotic normality and confidence region for Catoni's Z estimator
This paper studies the asymptotic property and confidence region of Catoni's Z estimator under the finite variance assumption. First, we investigate the CLT for Catoni's Z estimator with the asymptotically optimal variance, if the tuning parameter has order . Second, we propose the normal approximated confidence region of Catoni's Z estimator. The simulations show that the proposed 99% CLT‐based confidence regions are shorter than the existing non‐asymptotic confidence regions; mean squared errors of Catoni's Z estimators are typically smaller than sample means from heavy‐tailed data. Furthermore, the simulated coverage probabilities of the CLT‐based confidence region are close to the confidence levels when the sample size is moderately large. For 6‐year DOCVIS data (the number of doctor visits) in the German health care demand dataset, our CLT‐based confidence regions are tighter than non‐asymptotic confidence regions.
- Open Access
- 27 June 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (13) , 2252
Sharper Sub-Weibull Concentrations
Constant-specified and exponential concentration inequalities play an essential role in the finite-sample theory of machine learning and high-dimensional statistics area. We obtain sharper and constants-specified concentration inequalities for the sum of independent sub-Weibull random variables, which leads to a mixture of two tails: sub-Gaussian for small deviations and sub-Weibull for large deviations from the mean. These bounds are new and improve existing bounds with sharper constants. In addition, a new sub-Weibull parameter is also proposed, which enables recovering the tight concentration inequality for a random variable (vector). For statistical applications, we give an -error of estimated coefficients in negative binomial regressions when the heavy-tailed covariates are sub-Weibull distributed with sparse structures, which is a new result for negative binomial regressions. In applying random matrices, we derive non-asymptotic versions of Bai-Yin’s theorem for sub-Weibull entries with exponential tail bounds. Finally, by demonstrating a sub-Weibull confidence region for a log-truncated Z-estimator without the second-moment condition, we discuss and define the sub-Weibull type robust estimator for independent observations without exponential-moment conditions.- 27 June 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (13) , 2252
Open AccessSharper Sub-Weibull Concentrations
Constant-specified and exponential concentration inequalities play an essential role in the finite-sample theory of machine learning and high-dimensional statistics area. We obtain sharper and constants-specified concentration inequalities for the sum of independent sub-Weibull random variables, which leads to a mixture of two tails: sub-Gaussian for small deviations and sub-Weibull for large deviations from the mean. These bounds are new and improve existing bounds with sharper constants. In addition, a new sub-Weibull parameter is also proposed, which enables recovering the tight concentration inequality for a random variable (vector). For statistical applications, we give an -error of estimated coefficients in negative binomial regressions when the heavy-tailed covariates are sub-Weibull distributed with sparse structures, which is a new result for negative binomial regressions. In applying random matrices, we derive non-asymptotic versions of Bai-Yin’s theorem for sub-Weibull entries with exponential tail bounds. Finally, by demonstrating a sub-Weibull confidence region for a log-truncated Z-estimator without the second-moment condition, we discuss and define the sub-Weibull type robust estimator for independent observations without exponential-moment conditions. - Open Access
Sharper Sub-Weibull Concentrations
Constant-specified and exponential concentration inequalities play an essential role in the finite-sample theory of machine learning and high-dimensional statistics area. We obtain sharper and constants-specified concentration inequalities for the sum of independent sub-Weibull random variables, which leads to a mixture of two tails: sub-Gaussian for small deviations and sub-Weibull for large deviations from the mean. These bounds are new and improve existing bounds with sharper constants. In addition, a new sub-Weibull parameter if the italic should be retained. Please check the whole text. is also proposed, which enables recovering the tight concentration inequality for a random variable (vector). For statistical applications, we give an $\ell_2$-error of estimated coefficients in negative binomial regressions when the heavy-tailed covariates are sub-Weibull distributed with sparse structures, which is a new result for negative binomial regressions. In applying random matrices, we derive non-asymptotic versions of Bai-Yin's theorem for sub-Weibull entries with exponential tail bounds. Finally, by demonstrating a sub-Weibull confidence region for a log-truncated Z-estimator without the second-moment condition, we discuss and define the sub-Weibull type robust estimator for independent observations $\{X_i\}_{i=1}^{n}$ without exponential-moment conditions.Open AccessSharper Sub-Weibull Concentrations
Constant-specified and exponential concentration inequalities play an essential role in the finite-sample theory of machine learning and high-dimensional statistics area. We obtain sharper and constants-specified concentration inequalities for the sum of independent sub-Weibull random variables, which leads to a mixture of two tails: sub-Gaussian for small deviations and sub-Weibull for large deviations from the mean. These bounds are new and improve existing bounds with sharper constants. In addition, a new sub-Weibull parameter if the italic should be retained. Please check the whole text. is also proposed, which enables recovering the tight concentration inequality for a random variable (vector). For statistical applications, we give an $\ell_2$-error of estimated coefficients in negative binomial regressions when the heavy-tailed covariates are sub-Weibull distributed with sparse structures, which is a new result for negative binomial regressions. In applying random matrices, we derive non-asymptotic versions of Bai-Yin's theorem for sub-Weibull entries with exponential tail bounds. Finally, by demonstrating a sub-Weibull confidence region for a log-truncated Z-estimator without the second-moment condition, we discuss and define the sub-Weibull type robust estimator for independent observations $\{X_i\}_{i=1}^{n}$ without exponential-moment conditions. - Open Access
Sparse Density Estimation with Measurement Errors
This paper aims to estimate an unknown density of the data with measurement errors as a linear combination of functions from a dictionary. The main novelty is the proposal and investigation of the corrected sparse density estimator (CSDE). Inspired by the penalization approach, we propose the weighted Elastic-net penalized minimal -distance method for sparse coefficients estimation, where the adaptive weights come from sharp concentration inequalities. The first-order conditions holding a high probability obtain the optimal weighted tuning parameters. Under local coherence or minimal eigenvalue assumptions, non-asymptotic oracle inequalities are derived. These theoretical results are transposed to obtain the support recovery with a high probability. Some numerical experiments for discrete and continuous distributions confirm the significant improvement obtained by our procedure when compared with other conventional approaches. Finally, the application is performed in a meteorology dataset. It shows that our method has potency and superiority in detecting multi-mode density shapes compared with other conventional approaches.Open AccessSparse Density Estimation with Measurement Errors
This paper aims to estimate an unknown density of the data with measurement errors as a linear combination of functions from a dictionary. The main novelty is the proposal and investigation of the corrected sparse density estimator (CSDE). Inspired by the penalization approach, we propose the weighted Elastic-net penalized minimal -distance method for sparse coefficients estimation, where the adaptive weights come from sharp concentration inequalities. The first-order conditions holding a high probability obtain the optimal weighted tuning parameters. Under local coherence or minimal eigenvalue assumptions, non-asymptotic oracle inequalities are derived. These theoretical results are transposed to obtain the support recovery with a high probability. Some numerical experiments for discrete and continuous distributions confirm the significant improvement obtained by our procedure when compared with other conventional approaches. Finally, the application is performed in a meteorology dataset. It shows that our method has potency and superiority in detecting multi-mode density shapes compared with other conventional approaches.