Qiang Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qiang Wu has a total of 79 co-authors. Here are the top co-authors by number of shared publications:
- Ding-Xuan Zhou
School of Mathematics and Statistics, University of Sydney, Sydney, Australia
9 shared publications - Yiming Ying
SUNY Albany, Dept Math & Stat, Albany, NY 12222 USA
4 shared publications Hongwei Sun
School of Mathematical Science, University of Jinan and Shandong Provincial Key Laboratory of Network, Based Intelligent Computing, Jinan 250022, P. R. China
3 shared publications- Hongwei Sun
School of Mathematical Science
3 shared publications - Sayan Mukherjee
Leipzig University
3 shared publications Shanzhen Lu
Department of Mathematics, Beijing Normal University, Beijing 100875, China
3 shared publications
Latest Publications
- Open Access
- 31 March 2026
- Published by Springer Nature in Nature
- Vol. 652 (8110) , E7
Author Correction: Phenome-wide analysis of copy number variants in 470,727 UK Biobank genomes
- 31 March 2026
- Published by Springer Nature in Nature
- Vol. 652 (8110) , E7
Open AccessAuthor Correction: Phenome-wide analysis of copy number variants in 470,727 UK Biobank genomes
- Open Access
- 4 February 2026
- Published by Springer Nature in Nature
- Vol. 652 (8110) , 675-685
Phenome-wide analysis of copy number variants in 470,727 UK Biobank genomes
Copy number variants (CNVs) are key drivers of human diversity and disease risk1. Here we evaluate the role of CNVs across a broad range of human phenotypes and diseases by analysing CNVs from 470,727 UK Biobank whole-genome sequences and conducting a variant- and gene-level phenome-wide association study (PheWAS) with 2,941 plasma protein abundance measurements, 13,336 binary clinical phenotypes and 1,911 quantitative traits. Proteomic analyses validated functional associations of CNVs with nearby genes (cis-protein quantitative trait loci; cis-pQTLs)—with deletions and duplications typically associated with reduced and increased protein levels, respectively—and uncovered previously unknown protein–protein interactions (trans-pQTLs). Our PheWAS recapitulated known associations and uncovered associations in both coding and non-coding regions. Notably, we identified a rare deletion in ZNF451 associated with increased leukocyte telomere length and a non-coding deletion of a SLC2A9 enhancer associated with reduced gout risk. In addition, by combining CNVs with protein-coding single nucleotide variants and indels, we enhanced the power of our study to detect gene–disease associations. Finally, we leveraged this multiomics dataset to identify several pQTLs that constitute candidate biomarkers, including TMPRSS5 for Charcot–Marie–Tooth disease type 1A. This multiancestry whole-genome-sequence CNV PheWAS offers insights into the roles of CNVs in human health outcomes and could serve as a valuable resource for therapeutic development.
- 4 February 2026
- Published by Springer Nature in Nature
- Vol. 652 (8110) , 675-685
Open AccessPhenome-wide analysis of copy number variants in 470,727 UK Biobank genomes
Copy number variants (CNVs) are key drivers of human diversity and disease risk1. Here we evaluate the role of CNVs across a broad range of human phenotypes and diseases by analysing CNVs from 470,727 UK Biobank whole-genome sequences and conducting a variant- and gene-level phenome-wide association study (PheWAS) with 2,941 plasma protein abundance measurements, 13,336 binary clinical phenotypes and 1,911 quantitative traits. Proteomic analyses validated functional associations of CNVs with nearby genes (cis-protein quantitative trait loci; cis-pQTLs)—with deletions and duplications typically associated with reduced and increased protein levels, respectively—and uncovered previously unknown protein–protein interactions (trans-pQTLs). Our PheWAS recapitulated known associations and uncovered associations in both coding and non-coding regions. Notably, we identified a rare deletion in ZNF451 associated with increased leukocyte telomere length and a non-coding deletion of a SLC2A9 enhancer associated with reduced gout risk. In addition, by combining CNVs with protein-coding single nucleotide variants and indels, we enhanced the power of our study to detect gene–disease associations. Finally, we leveraged this multiomics dataset to identify several pQTLs that constitute candidate biomarkers, including TMPRSS5 for Charcot–Marie–Tooth disease type 1A. This multiancestry whole-genome-sequence CNV PheWAS offers insights into the roles of CNVs in human health outcomes and could serve as a valuable resource for therapeutic development.
- 17 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2872-2876
Fitness-Assisted Counting Based on Lightweight Pose Recognition Network and k-NN Classification
In this paper, propose a fitness assistance algorithm based on the combination of a lightweight network human posture detection model, BlazePose, and a k-NN classification algorithm for real-time counting on mobile devices. Firstly, the BlazePose model is used to predict the target pose on the given sample image, and the obtained Landmark is normalized to build the training set of the k-NN classifier. Then Pose Classification Colab classifies each sample by targeting the entire training set while excluding outliers and underrepresented categories. Finally, the implementation of the classifier itself can realize the real-time counting of fitness exercises. In this study, squats and push-ups, two of the most representative sports, are selected as the verification objects. The experimental results show that, with real-time and accuracy guaranteed This algorithm is capable of classifying and counting push-ups and squats at a rate of 30 frames on an ordinary mobile device.
- 17 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2872-2876
Fitness-Assisted Counting Based on Lightweight Pose Recognition Network and k-NN Classification
In this paper, propose a fitness assistance algorithm based on the combination of a lightweight network human posture detection model, BlazePose, and a k-NN classification algorithm for real-time counting on mobile devices. Firstly, the BlazePose model is used to predict the target pose on the given sample image, and the obtained Landmark is normalized to build the training set of the k-NN classifier. Then Pose Classification Colab classifies each sample by targeting the entire training set while excluding outliers and underrepresented categories. Finally, the implementation of the classifier itself can realize the real-time counting of fitness exercises. In this study, squats and push-ups, two of the most representative sports, are selected as the verification objects. The experimental results show that, with real-time and accuracy guaranteed This algorithm is capable of classifying and counting push-ups and squats at a rate of 30 frames on an ordinary mobile device.
- 13 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 33 (10) , 6038-6043
Fast Rates of Gaussian Empirical Gain Maximization With Heavy-Tailed Noise
In a regression setup, we study in this brief the performance of Gaussian empirical gain maximization (EGM), which includes a broad variety of well-established robust estimation approaches. In particular, we conduct a refined learning theory analysis for Gaussian EGM, investigate its regression calibration properties, and develop improved convergence rates in the presence of heavy-tailed noise. To achieve these purposes, we first introduce a new weak moment condition that could accommodate the cases where the noise distribution may be heavy-tailed. Based on the moment condition, we then develop a novel comparison theorem that can be used to characterize the regression calibration properties of Gaussian EGM. It also plays an essential role in deriving improved convergence rates. Therefore, the present study broadens our theoretical understanding of Gaussian EGM.
- 13 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 33 (10) , 6038-6043
Fast Rates of Gaussian Empirical Gain Maximization With Heavy-Tailed Noise
In a regression setup, we study in this brief the performance of Gaussian empirical gain maximization (EGM), which includes a broad variety of well-established robust estimation approaches. In particular, we conduct a refined learning theory analysis for Gaussian EGM, investigate its regression calibration properties, and develop improved convergence rates in the presence of heavy-tailed noise. To achieve these purposes, we first introduce a new weak moment condition that could accommodate the cases where the noise distribution may be heavy-tailed. Based on the moment condition, we then develop a novel comparison theorem that can be used to characterize the regression calibration properties of Gaussian EGM. It also plays an essential role in deriving improved convergence rates. Therefore, the present study broadens our theoretical understanding of Gaussian EGM.
- 26 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 20 (2) , 1581-1586
Attention Deficit Hyperactivity Disorder Classification Based on Deep Learning
Attention Deficit Hyperactivity Disorder (ADHD) is a type of mental health disorder that can be seen from children to adults. Accurate diagnosis of ADHD as early as possible is very important for the treatment of patients in clinical applications. In this paper, we propose two novel deep learning approaches for ADHD classification based on functional magnetic resonance imaging (fMRI). The first method incorporates independent component analysis with convolutional neural network. It first extracts independent components from each subject. The independent components are then fed into a convolutional neural network as input features to classify the ADHD patients from typical controls. The second method, called the correlation autoencoder method, uses correlations between regions of interest of the brain as the input of an autoencoder to learn latent features, which are then used in the classification task by a new neural network. These two methods use different ways to extract the inter-voxel information from fMRI, but both use convolutional neural networks to further extract predictive features for the classification task. Empirical experiments show that both methods are able to outperform the classical methods such as logistic regression, support vector machines, and some other methods used in previous studies.
- 26 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 20 (2) , 1581-1586
Attention Deficit Hyperactivity Disorder Classification Based on Deep Learning
Attention Deficit Hyperactivity Disorder (ADHD) is a type of mental health disorder that can be seen from children to adults. Accurate diagnosis of ADHD as early as possible is very important for the treatment of patients in clinical applications. In this paper, we propose two novel deep learning approaches for ADHD classification based on functional magnetic resonance imaging (fMRI). The first method incorporates independent component analysis with convolutional neural network. It first extracts independent components from each subject. The independent components are then fed into a convolutional neural network as input features to classify the ADHD patients from typical controls. The second method, called the correlation autoencoder method, uses correlations between regions of interest of the brain as the input of an autoencoder to learn latent features, which are then used in the classification task by a new neural network. These two methods use different ways to extract the inter-voxel information from fMRI, but both use convolutional neural networks to further extract predictive features for the classification task. Empirical experiments show that both methods are able to outperform the classical methods such as logistic regression, support vector machines, and some other methods used in previous studies.
- 18 February 2022
- Published by Springer Nature in Computational Economics
- Vol. 61 (3) , 1137-1150
Prediction of Loan Rate for Mortgage Data: Deep Learning Versus Robust Regression
- 18 February 2022
- Published by Springer Nature in Computational Economics
- Vol. 61 (3) , 1137-1150
Prediction of Loan Rate for Mortgage Data: Deep Learning Versus Robust Regression
- Open Access
- 13 May 2021
- Published by MIT Press in Neural Computation
- Vol. 33 (6) , 1656-1697
A Framework of Learning Through Empirical Gain Maximization
We develop in this letter a framework of empirical gain maximization (EGM) to address the robust regression problem where heavy-tailed noise or outliers may be present in the response variable. The idea of EGM is to approximate the density function of the noise distribution instead of approximating the truth function directly as usual. Unlike the classical maximum likelihood estimation that encourages equal importance of all observations and could be problematic in the presence of abnormal observations, EGM schemes can be interpreted from a minimum distance estimation viewpoint and allow the ignorance of those observations. Furthermore, we show that several well-known robust nonconvex regression paradigms, such as Tukey regression and truncated least square regression, can be reformulated into this new framework. We then develop a learning theory for EGM by means of which a unified analysis can be conducted for these well-established but not fully understood regression approaches. This new framework leads to a novel interpretation of existing bounded nonconvex loss functions. Within this new framework, the two seemingly irrelevant terminologies, the well-known Tukey's biweight loss for robust regression and the triweight kernel for nonparametric smoothing, are closely related. More precisely, we show that Tukey's biweight loss can be derived from the triweight kernel. Other frequently employed bounded nonconvex loss functions in machine learning, such as the truncated square loss, the Geman-McClure loss, and the exponential squared loss, can also be reformulated from certain smoothing kernels in statistics. In addition, the new framework enables us to devise new bounded nonconvex loss functions for robust learning.
- 13 May 2021
- Published by MIT Press in Neural Computation
- Vol. 33 (6) , 1656-1697
Open AccessA Framework of Learning Through Empirical Gain Maximization
We develop in this letter a framework of empirical gain maximization (EGM) to address the robust regression problem where heavy-tailed noise or outliers may be present in the response variable. The idea of EGM is to approximate the density function of the noise distribution instead of approximating the truth function directly as usual. Unlike the classical maximum likelihood estimation that encourages equal importance of all observations and could be problematic in the presence of abnormal observations, EGM schemes can be interpreted from a minimum distance estimation viewpoint and allow the ignorance of those observations. Furthermore, we show that several well-known robust nonconvex regression paradigms, such as Tukey regression and truncated least square regression, can be reformulated into this new framework. We then develop a learning theory for EGM by means of which a unified analysis can be conducted for these well-established but not fully understood regression approaches. This new framework leads to a novel interpretation of existing bounded nonconvex loss functions. Within this new framework, the two seemingly irrelevant terminologies, the well-known Tukey's biweight loss for robust regression and the triweight kernel for nonparametric smoothing, are closely related. More precisely, we show that Tukey's biweight loss can be derived from the triweight kernel. Other frequently employed bounded nonconvex loss functions in machine learning, such as the truncated square loss, the Geman-McClure loss, and the exponential squared loss, can also be reformulated from certain smoothing kernels in statistics. In addition, the new framework enables us to devise new bounded nonconvex loss functions for robust learning.
- Open Access
A Framework of Learning Through Empirical Gain Maximization
We develop in this paper a framework of empirical gain maximization (EGM) to address the robust regression problem where heavy-tailed noise or outliers may present in the response variable. The idea of EGM is to approximate the density function of the noise distribution instead of approximating the truth function directly as usual. Unlike the classical maximum likelihood estimation that encourages equal importance of all observations and could be problematic in the presence of abnormal observations, EGM schemes can be interpreted from a minimum distance estimation viewpoint and allow the ignorance of those observations. Furthermore, it is shown that several well-known robust nonconvex regression paradigms, such as Tukey regression and truncated least square regression, can be reformulated into this new framework. We then develop a learning theory for EGM, by means of which a unified analysis can be conducted for these well-established but not fully-understood regression approaches. Resulting from the new framework, a novel interpretation of existing bounded nonconvex loss functions can be concluded. Within this new framework, the two seemingly irrelevant terminologies, the well-known Tukey's biweight loss for robust regression and the triweight kernel for nonparametric smoothing, are closely related. More precisely, it is shown that the Tukey's biweight loss can be derived from the triweight kernel. Similarly, other frequently employed bounded nonconvex loss functions in machine learning such as the truncated square loss, the Geman-McClure loss, and the exponential squared loss can also be reformulated from certain smoothing kernels in statistics. In addition, the new framework enables us to devise new bounded nonconvex loss functions for robust learning.
Open AccessA Framework of Learning Through Empirical Gain Maximization
We develop in this paper a framework of empirical gain maximization (EGM) to address the robust regression problem where heavy-tailed noise or outliers may present in the response variable. The idea of EGM is to approximate the density function of the noise distribution instead of approximating the truth function directly as usual. Unlike the classical maximum likelihood estimation that encourages equal importance of all observations and could be problematic in the presence of abnormal observations, EGM schemes can be interpreted from a minimum distance estimation viewpoint and allow the ignorance of those observations. Furthermore, it is shown that several well-known robust nonconvex regression paradigms, such as Tukey regression and truncated least square regression, can be reformulated into this new framework. We then develop a learning theory for EGM, by means of which a unified analysis can be conducted for these well-established but not fully-understood regression approaches. Resulting from the new framework, a novel interpretation of existing bounded nonconvex loss functions can be concluded. Within this new framework, the two seemingly irrelevant terminologies, the well-known Tukey's biweight loss for robust regression and the triweight kernel for nonparametric smoothing, are closely related. More precisely, it is shown that the Tukey's biweight loss can be derived from the triweight kernel. Similarly, other frequently employed bounded nonconvex loss functions in machine learning such as the truncated square loss, the Geman-McClure loss, and the exponential squared loss can also be reformulated from certain smoothing kernels in statistics. In addition, the new framework enables us to devise new bounded nonconvex loss functions for robust learning.
- 1 January 2021
- Published by International Press of Boston in Communications in Mathematical Sciences
- Vol. 19 (6) , 1533-1548
Regularized least square kernel regression for streaming data
- 1 January 2021
- Published by International Press of Boston in Communications in Mathematical Sciences
- Vol. 19 (6) , 1533-1548
Regularized least square kernel regression for streaming data
- 29 December 2020
- Published by Elsevier in Journal of Approximation Theory
- Vol. 263, 105518
Kernel gradient descent algorithm for information theoretic learning
- 29 December 2020
- Published by Elsevier in Journal of Approximation Theory
- Vol. 263, 105518
Kernel gradient descent algorithm for information theoretic learning