Zheng Wang

Dr. Zheng Wang

College of Electronic and Information Engineering, Southwest University, Chongqing, China
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
14 October 2019 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
HLHuaqing Li
Huaqing Li
Zheng WangZheng Wang
Zheng Wang
GCGuo Chen
Guo Chen
Zhaoyang DongZhaoyang Dong
Zhaoyang Dong

5 August 2019 in IEEE Transactions on Network Science and Engineering
Verified
Journal Article
Closed access
Zheng WangZheng Wang
Zheng Wang
HLHuaqing Li
Huaqing Li
This paper investigates distributed optimization problems where a group of networked nodes collaboratively minimizes the sum of all local objective functions. The local objective function of each node is further set as an average of a finite set of subfunctions. This adjustment is motivated by machine learning problems with large training samples distributed and known privately to individual computational nodes. An augmented Lagrange (AL) stochastic gradient algorithm is presented to address the distributed optimization problem, which is integrated with the factorization of weighted Laplacian and local unbiased stochastic averaging gradient methods. At each iteration, only one randomly selected gradient of a subfunction is evaluated at a node, and a variance-reduced stochastic averaging gradient technique is applied to approximating the gradient of local objective function. Strong convexity of the local subfunction and Lipschitz continuity of its gradient are shown to ensure a linear convergence rate of the proposed algorithm in expectation. Numerical experiments on a logistic regression problem demonstrate the correctness of theoretical results.

13 October 2020 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
HLHuaqing Li
Huaqing Li
HCHuqiang Cheng
Huqiang Cheng
Zheng WangZheng Wang
Zheng Wang
GWGuo-Cheng Wu
Guo-Cheng Wu
In this article, we come up with a novel Nesterov gradient and heavy-ball double accelerated distributed synchronous optimization algorithm, called NHDA, and adopt a general asynchronous model to further propose an effective asynchronous algorithm, called ASY-NHDA, for distributed optimization problem over directed graphs, where each agent has access to a local objective function and computes the optimal solution via communicating only with its immediate neighbors. Our goal is to minimize a sum of all local objective functions satisfying strong convexity and Lipschitz continuity. Consider a general asynchronous model, where agents communicate with their immediate neighbors and start a new computation independently, that is, agents can communicate with their neighbors at any time without any coordination and use delayed information from their in-neighbors to compute a new update. Delays are arbitrary, unpredictable, and time-varying but bounded. The theoretical analysis of NHDA is based on analyzing the interaction among the consensus, the gradient tracking, and the optimization processes. As for the analysis of ASY-NHDA, we equivalently transform the asynchronous system into an augmented synchronous system without delays and prove its convergence through using the generalized small gain theorem. The results show that NHDA and ASY-NHDA converge to the optimal solution at a linear convergence as long as the largest step size is positive and less than an explicitly estimated upper bound, and the largest momentum parameter is nonnegative and less than an upper bound. Finally, we demonstrate the advantages of ASY-NHDA through simulations.

3 September 2020 in IEEE Transactions on Emerging Topics in Computational Intelligence
Verified
Journal Article
Closed access
HLHuaqing Li
Huaqing Li
LZLifeng Zheng
Lifeng Zheng
Zheng WangZheng Wang
Zheng Wang
YYYu Yan
Yu Yan
LFLiping Feng
Liping Feng
JGJing Guo
Jing Guo
In this article, we study convex optimization problems where agents of a network cooperatively minimize the global objective function which consists of multiple local objective functions. The intention of this work is to solve large-scale optimization problems where the local objective function is complicated, and numerous. Different from most of the existing works, the local objective function of each agent is presented as the average of finite instantaneous functions. Integrating the gradient tracking algorithm with stochastic averaging gradient technology, a distributed stochastic gradient tracking (termed as S-DIGing) algorithm is proposed. At each time instant, only one randomly selected gradient of an instantaneous function is computed, and applied to approximate the local batch gradient for each agent. Based on a novel primal-dual interpretation of the S-DIGing algorithm, it is shown that the S-DIGing algorithm linearly converges to the global optimal solution when step-size do not exceed an explicit upper bound, and the instantaneous functions are strongly convex with Lipschitz continuous gradients. Numerical experiments are presented to demonstrate the practicability of the S-DIGing algorithm, and correctness of the theoretical results.

26 October 2021 in IEEE Transactions on Signal and Information Processing over Networks
Verified
Journal Article
Closed access
HLHuaqing Li
Huaqing Li
LZLifeng Zheng
Lifeng Zheng
Zheng WangZheng Wang
Zheng Wang
YLYongfu Li
Yongfu Li
LJLianghao Ji
Lianghao Ji
DXDawen Xia
Dawen Xia
Considering the extensive applications of the model predictive control (MPC), this paper investigates the MPC problem with an application to the optimal output consensus of high-order multi-agent systems. A synchronous distributed optimization algorithm for the MPC problem is proposed, and we further devise its asynchronous version. The algorithm allows agents to choose the uncoordinate step-sizes depending on local information, which improves the flexibility of multi-agent systems. The convergence of the proposed algorithm is guaranteed if the positive uncoordinate step-sizes satisfy the explicit conditions. Compared with the synchronous version that needs a global clock to control all agents for communication and update, the asynchronous algorithm does not require each agent in the multi-agent systems to update and communicate simultaneously, and also converges to the optimal global solution to the problem. The numerical simulations demonstrate the availability of the proposed algorithm and the validity of the theoretical results.

16 January 2020 in IEEE Transactions on Signal and Information Processing over Networks
Verified
Journal Article
Closed access
HLHuaqing Li
Huaqing Li
CHChicheng Huang
Chicheng Huang
Zheng WangZheng Wang
Zheng Wang
GCGuo Chen
Guo Chen
HUHafiz Gulfam Ahmad Umar
Hafiz Gulfam Ahmad Umar
A novel computation-efficient quantized distributed optimization algorithm is presented in this paper for solving a class of convex optimization problems over time-varying undirected networks with limited communication capacity. These convex optimization problems are usually relevant to the minimization of a sum of local convex objective functions using only local communication and local computation. In most of the existing distributed optimization algorithms, each agent needs to calculate the subgradient of its local convex objective function at each time step, which leads to extremely heavy computation. The proposed algorithm incorporates random sleep scheme into procedures of agents' updates in a probabilistic form to reduce the computation load, and further allows for uncoordinated step-sizes of all agents. The quantized strategy is also applied, which overcomes the limitation of communication capacity. Theoretical analysis indicates that the convex optimization problems can be solved and numerical analysis shows that the computation load of subgradient can be significantly reduced by the proposed algorithm. The boundedness of the quantization levels at each time step has been explicitly characterized. Simulation examples are presented to demonstrate the effectiveness of the algorithm and the correctness of the theoretical results.