CJCui Jia
Cui Jia
*This is an algorithmically generated author record based on publicly available information.
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
Cui Jia has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Zhuo-Xu Cui
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
2 shared publications - Li Zhu
School of Statistics and Data Science, Ningbo University of Technology, No. 201, Fenghua Road, Jiangbei District, Ningbo 315211, China
1 shared publication - Qibin Fan
Wuhan University
1 shared publication
Latest Publications
- Open Access
- 10 July 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (14) , 2168
Data-Driven Method for Robust Recovery in 1-Bit Compressive Sensing with the Minimax Concave Penalty
With the advent of large-scale data, the demand for information is increasing, which makes signal sampling technology and digital processing methods particularly important. The utilization of 1-bit compressive sensing in sparse recovery has garnered significant attention due to its cost-effectiveness in hardware implementation and storage. In this paper, we first leverage the minimax concave penalty equipped with the least squares to recover a high-dimensional true signal with k-sparse from n-dimensional 1-bit measurements and discuss the regularization by combing the nonconvex sparsity-inducing penalties. Moreover, we give an analysis of the complexity of the method with minimax concave penalty in certain conditions and derive the general theory for the model equipped with the family of sparsity-inducing nonconvex functions. Then, our approach employs a data-driven Newton-type method with stagewise steps to solve the proposed method. Numerical experiments on the synthesized and real data verify the competitiveness of the proposed method.- 10 July 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (14) , 2168
Open AccessData-Driven Method for Robust Recovery in 1-Bit Compressive Sensing with the Minimax Concave Penalty
With the advent of large-scale data, the demand for information is increasing, which makes signal sampling technology and digital processing methods particularly important. The utilization of 1-bit compressive sensing in sparse recovery has garnered significant attention due to its cost-effectiveness in hardware implementation and storage. In this paper, we first leverage the minimax concave penalty equipped with the least squares to recover a high-dimensional true signal with k-sparse from n-dimensional 1-bit measurements and discuss the regularization by combing the nonconvex sparsity-inducing penalties. Moreover, we give an analysis of the complexity of the method with minimax concave penalty in certain conditions and derive the general theory for the model equipped with the family of sparsity-inducing nonconvex functions. Then, our approach employs a data-driven Newton-type method with stagewise steps to solve the proposed method. Numerical experiments on the synthesized and real data verify the competitiveness of the proposed method. - Open Access
- 27 May 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (11) , 1664
Stagewise Accelerated Stochastic Gradient Methods for Nonconvex Optimization
For large-scale optimization that covers a wide range of optimization problems encountered frequently in machine learning and deep neural networks, stochastic optimization has become one of the most used methods thanks to its low computational complexity. In machine learning and deep learning problems, nonconvex problems are common, while convex problems are rare. How to find the global minimum for nonconvex optimization and reduce the computational complexity are challenges. Inspired by the phenomenon that the stagewise stepsize tuning strategy can empirically improve the convergence speed in deep neural networks, we incorporate the stagewise stepsize tuning strategy into the iterative framework of Nesterov’s acceleration- and variance reduction-based methods to reduce the computational complexity, i.e., the stagewise stepsize tuning strategy is incorporated into randomized stochastic accelerated gradient and stochastic variance-reduced gradient. The proposed methods are theoretically derived to reduce the complexity of the nonconvex and convex problems and improve the convergence rate of the frameworks, which have the complexity and , respectively, where is the PL modulus and L is the Lipschitz constant. In the end, numerical experiments on large benchmark datasets validate well the competitiveness of the proposed methods.- 27 May 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (11) , 1664
Open AccessStagewise Accelerated Stochastic Gradient Methods for Nonconvex Optimization
For large-scale optimization that covers a wide range of optimization problems encountered frequently in machine learning and deep neural networks, stochastic optimization has become one of the most used methods thanks to its low computational complexity. In machine learning and deep learning problems, nonconvex problems are common, while convex problems are rare. How to find the global minimum for nonconvex optimization and reduce the computational complexity are challenges. Inspired by the phenomenon that the stagewise stepsize tuning strategy can empirically improve the convergence speed in deep neural networks, we incorporate the stagewise stepsize tuning strategy into the iterative framework of Nesterov’s acceleration- and variance reduction-based methods to reduce the computational complexity, i.e., the stagewise stepsize tuning strategy is incorporated into randomized stochastic accelerated gradient and stochastic variance-reduced gradient. The proposed methods are theoretically derived to reduce the complexity of the nonconvex and convex problems and improve the convergence rate of the frameworks, which have the complexity and , respectively, where is the PL modulus and L is the Lipschitz constant. In the end, numerical experiments on large benchmark datasets validate well the competitiveness of the proposed methods. - 23 April 2020
- Published by Elsevier in Signal Processing
- Vol. 174, 107614
Momentum methods for stochastic optimization over time-varying directed networks
- 23 April 2020
- Published by Elsevier in Signal Processing
- Vol. 174, 107614
Momentum methods for stochastic optimization over time-varying directed networks