Xu Zhang

Prof. Xu Zhang

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 March 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
XLXiaofeng Liu
Xiaofeng Liu
YLYinchuan Li
Yinchuan Li
QWQing Wang
Qing Wang
Xu ZhangXu Zhang
Xu Zhang
YSYunfeng Shao
Yunfeng Shao
YGYanhui Geng
Yanhui Geng
Federated learning (FL) is a collaborative machine learning technique to train a global model (GM) without obtaining clients’ private data. The main challenges in FL are statistical diversity among clients, limited computing capability among clients’ equipment, and the excessive communication overhead between the server and clients. To address these challenges, we propose a novel sparse personalized FL scheme via maximizing correlation (FedMac). By incorporating an approximated $\ell_1$ -norm and the correlation between client models and GM into standard FL loss function, the performance on statistical diversity data is improved and the communicational and computational loads required in the network are reduced compared with nonsparse FL. Convergence analysis shows that the sparse constraints in FedMac do not affect the convergence rate of the GM, and theoretical results show that FedMac can achieve good sparse personalization, which is better than the personalized methods based on the $\ell_2$ -norm. Experimentally, we demonstrate the benefits of this sparse personalization architecture compared with the state-of-the-art personalization methods (e.g., FedMac, respectively, achieves 98.95%, 99.37%, 90.90%, 89.06%, and 73.52% accuracy on the MNIST, FMNIST, CIFAR-100, Synthetic, and CINIC-10 datasets under non-independent and identically distributed (i.i.d.) variants).

29 March 2021 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
Xu ZhangXu Zhang
Xu Zhang
YLYulong Liu
Yulong Liu
WCWei Cui
Wei Cui
This article studies the problem of reconstructing spectrally sparse signals from a small random subset of time domain samples via low-rank Hankel matrix completion with the aid of prior information. By leveraging the low-rank structure of spectrally sparse signals in the lifting domain and the similarity between the signals and their prior information, we propose a convex method to recover the undersampled spectrally sparse signals. The proposed approach integrates the inner product of the desired signal and its prior information in the lift domain into vanilla Hankel matrix completion, which maximizes the correlation between the signals and their prior information. Theoretical analysis indicates that when the prior information is reliable, the proposed method has a better performance than vanilla Hankel matrix completion, which reduces the number of measurements by a logarithmic factor. We also develop an ADMM algorithm to solve the corresponding optimization problem. Numerical results are provided to verify the performance of proposed method and corresponding algorithm.

27 July 2021 in IEEE Transactions on Control of Network Systems
Verified
Journal Article
Closed access
Xu ZhangXu Zhang
Xu Zhang
MVMarcos M. Vasconcelos
Marcos M. Vasconcelos
WCWei Cui
Wei Cui
UMUrbashi Mitra
Urbashi Mitra
Internet of Things networks are the large-scale distributed systems consisting of a massive number of simple devices communicating, typically, over a shared wireless medium. This new paradigm requires novel ways of coordinating access to limited communication resources without introducing unreasonable delays. Herein, the optimal design of a remote estimation system with $n$ sensors communicating with a fusion center via a collision channel of limited capacity $k\leq n$ is considered. In particular, for independent and identically distributed observations with a symmetric probability density function, we show that the problem of minimizing the mean-squared error with respect to a threshold strategy is quasi-convex. When coordination among sensors via a local communication network is available, the online learning of possibly unknown parameters of the probabilistic model is possible, enabling each sensor to optimize its own threshold autonomously. We propose two strategies for remote estimation with local communication: 1) one strategy swiftly reaches the performance of the optimal decentralized threshold policy and 2) the second strategy approaches the performance of the optimal centralized scheme with a slower convergence rate. A hybrid scheme that combines the best of both approaches is proposed, offering fast convergence and excellent performance.

2 May 2018 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
Xu ZhangXu Zhang
Xu Zhang
WCWei Cui
Wei Cui
YLYulong Liu
Yulong Liu
This paper considers the problem of recovering a structured signal from a relatively small number of noisy measurements with the aid of a similar signal which is known beforehand. We propose a new approach to integrate prior information into the standard recovery procedure by maximizing the correlation between the prior knowledge and the desired signal. We then establish performance guarantees (in terms of the number of measurements) for the proposed method under sub-Gaussian measurements. Specific structured signals including sparse vectors, block-sparse vectors, and low-rank matrices are also analyzed. Furthermore, we present an interesting geometrical interpretation for the proposed procedure. Our results demonstrate that if prior information is good enough, then the proposed approach can (remarkably) outperform the standard recovery procedure. Simulations are provided to verify our results.

18 March 2024 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
JLJinsheng Li
Jinsheng Li
WCWei Cui
Wei Cui
Xu ZhangXu Zhang
Xu Zhang
Current spectral compressed sensing methods via Hankel matrix completion employ symmetric factorization to demonstrate the low-rank property of the Hankel matrix. However, previous non-convex gradient methods only utilize asymmetric factorization to achieve spectral compressed sensing. In this paper, we propose a novel nonconvex projected gradient descent method for spectral compressed sensing via symmetric factorization named Symmetric Hankel Projected Gradient Descent (SHGD), which updates only one matrix and avoids a balancing regularization term. SHGD reduces about half of the computation and storage costs compared to the prior gradient method based on asymmetric factorization. Besides, the symmetric factorization employed in our work is completely novel to the prior low-rank factorization model, introducing a new factorization ambiguity under complex orthogonal transformation. Novel distance metrics are designed for our factorization method and a linear convergence guarantee to the desired signal is established with O ( r 2 log( n )) observations. Numerical simulations demonstrate the superior performance of the proposed SHGD method in phase transitions and computation efficiency compared to state-of-the-art methods.

7 March 2019 in IEEE Transactions on Signal Processing
Verified
Journal Article
Open access
WCWei Cui
Wei Cui
Xu ZhangXu Zhang
Xu Zhang
YLYulong Liu
Yulong Liu
Covariance matrix estimation concerns the problem of estimating the covariance matrix from a collection of samples, which is of extreme importance in many applications. Classical results have shown that $O(n)$ samples are sufficient to accurately estimate the covariance matrix from $n$ -dimensional independent Gaussian samples. However, in many practical applications, the received signal samples might be correlated, which makes the classical analysis inapplicable. In this paper, we develop a non-asymptotic analysis for the covariance matrix estimation from linearly-correlated Gaussian samples. Our theoretical results show that the error bounds are determined by the signal dimension $n$ , the sample size $m$ , and the shape parameter of the distribution of the correlated sample covariance matrix. Particularly, when the shape parameter is a class of Toeplitz matrices (which is of great practical interest), $O(n)$ samples are also sufficient to faithfully estimate the covariance matrix from correlated samples. Simulations are provided to verify the correctness of the theoretical results.