Deliang Wei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Deliang Wei has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Fang Li
School of Mathematical Sciences, Key Laboratory of MEA & Shanghai Key Laboratory of PMMP, East China Normal University, Shanghai, China
7 shared publications - Peng Chen
School of Mathematical Sciences, Key Laboratory of Ministry of Education (MEA), and Shanghai Key Laboratory of PMMP, East China Normal University, Shanghai, China
3 shared publications Changhong Lu
East China Normal Univ, Sch Math Sci, Key Lab MEA, Minist Educ, Shanghai 200241, Peoples R China
1 shared publication- Changhong Lu
School of Mathematical Sciences, Key Laboratory of MEA (Ministry of Education), Shanghai Key Laboratory of PMMP, and Nantong Institute for Applied Mathematics and Artificial Intelligence, East China Normal University, Shanghai, China
1 shared publication Peng Chen
School of Mathematical Sciences Ministry of Education Key Laboratory of Mathematics and Engi- neering Applications Shanghai Key Laboratory of PMMP East China Normal University 200241 Shanghai China
1 shared publicationShiyang Weng
1 shared publication
Latest Publications
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (2) , 2690-2706
Low-Rank and Deep Plug-and-Play Priors for Missing Traffic Data Imputation
The development of sensor technology has resulted in the accumulation of extensive spatiotemporal traffic information, which holds great potential for predicting traffic patterns and improving traffic management strategies. Nevertheless, dealing with missing data poses a significant challenge for the intelligent traffic system (ITS). To address this issue, this study employs a nonconvex smoothly clipped absolute deviation (SCAD) penalty customized for tensors to surrogate tensor rank and incorporates the deep plug-and-play (PnP) prior into the low-rank tensor completion (LRTC) model. An efficient iterative framework is formulated to integrate these penalties into the alternating direction method of multipliers (ADMM) method. Moreover, two imputation methods, namely LRTC-SCAD and LRTC-SCAD-DeepPnP, are developed, affirming that the LRTC-SCAD method ensures convergence to the global optimum. We conduct simulated experiments using real-world traffic datasets, and our proposed methods outperform state-of-the-art imputation methods. For instance, on the Portland dataset, LRTC-SCAD achieves a noteworthy 9.86% improvement in mean absolute percentage error (MAPE) compared to the cutting-edge LRTC method while consuming only 28.26% of its total running time. Similarly, on the PeMS dataset, LRTC-SCAD-DeepPnP achieves an average 11.59% enhancement in MAPE, with visually compelling improvements in imputation results, further validating its efficacy in maintaining local consistency. The code is available at https://github.com/peterchen96/LRTC_DeepPnP.
- 18 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (2) , 2690-2706
Low-Rank and Deep Plug-and-Play Priors for Missing Traffic Data Imputation
The development of sensor technology has resulted in the accumulation of extensive spatiotemporal traffic information, which holds great potential for predicting traffic patterns and improving traffic management strategies. Nevertheless, dealing with missing data poses a significant challenge for the intelligent traffic system (ITS). To address this issue, this study employs a nonconvex smoothly clipped absolute deviation (SCAD) penalty customized for tensors to surrogate tensor rank and incorporates the deep plug-and-play (PnP) prior into the low-rank tensor completion (LRTC) model. An efficient iterative framework is formulated to integrate these penalties into the alternating direction method of multipliers (ADMM) method. Moreover, two imputation methods, namely LRTC-SCAD and LRTC-SCAD-DeepPnP, are developed, affirming that the LRTC-SCAD method ensures convergence to the global optimum. We conduct simulated experiments using real-world traffic datasets, and our proposed methods outperform state-of-the-art imputation methods. For instance, on the Portland dataset, LRTC-SCAD achieves a noteworthy 9.86% improvement in mean absolute percentage error (MAPE) compared to the cutting-edge LRTC method while consuming only 28.26% of its total running time. Similarly, on the PeMS dataset, LRTC-SCAD-DeepPnP achieves an average 11.59% enhancement in MAPE, with visually compelling improvements in imputation results, further validating its efficacy in maintaining local consistency. The code is available at https://github.com/peterchen96/LRTC_DeepPnP.
- 22 May 2024
- Published by Elsevier in Transportation Research Part C: Emerging Technologies
- Vol. 164
Spatiotemporal traffic data completion with truncated minimax-concave penalty
- 22 May 2024
- Published by Elsevier in Transportation Research Part C: Emerging Technologies
- Vol. 164
Spatiotemporal traffic data completion with truncated minimax-concave penalty
- Open Access
Learning pseudo-contractive denoisers for inverse problems
Deep denoisers have shown excellent performance in solving inverse problems in signal and image processing. In order to guarantee the convergence, the denoiser needs to satisfy some Lipschitz conditions like non-expansiveness. However, enforcing such constraints inevitably compromises recovery performance. This paper introduces a novel training strategy that enforces a weaker constraint on the deep denoiser called pseudo-contractiveness. By studying the spectrum of the Jacobian matrix, relationships between different denoiser assumptions are revealed. Effective algorithms based on gradient descent and Ishikawa process are derived, and further assumptions of strict pseudo-contractiveness yield efficient algorithms using half-quadratic splitting and forward-backward splitting. The proposed algorithms theoretically converge strongly to a fixed point. A training strategy based on holomorphic transformation and functional calculi is proposed to enforce the pseudo-contractive denoiser assumption. Extensive experiments demonstrate superior performance of the pseudo-contractive denoiser compared to related denoisers. The proposed methods are competitive in terms of visual effects and quantitative values.
Open AccessLearning pseudo-contractive denoisers for inverse problems
Deep denoisers have shown excellent performance in solving inverse problems in signal and image processing. In order to guarantee the convergence, the denoiser needs to satisfy some Lipschitz conditions like non-expansiveness. However, enforcing such constraints inevitably compromises recovery performance. This paper introduces a novel training strategy that enforces a weaker constraint on the deep denoiser called pseudo-contractiveness. By studying the spectrum of the Jacobian matrix, relationships between different denoiser assumptions are revealed. Effective algorithms based on gradient descent and Ishikawa process are derived, and further assumptions of strict pseudo-contractiveness yield efficient algorithms using half-quadratic splitting and forward-backward splitting. The proposed algorithms theoretically converge strongly to a fixed point. A training strategy based on holomorphic transformation and functional calculi is proposed to enforce the pseudo-contractive denoiser assumption. Extensive experiments demonstrate superior performance of the pseudo-contractive denoiser compared to related denoisers. The proposed methods are competitive in terms of visual effects and quantitative values.
- 27 July 2023
- Published by Springer Nature in Journal of Scientific Computing
- Vol. 96 (3) , 1-27
Cauchy Noise Removal via Convergent Plug-and-Play Framework with Outliers Detection
- 27 July 2023
- Published by Springer Nature in Journal of Scientific Computing
- Vol. 96 (3) , 1-27
Cauchy Noise Removal via Convergent Plug-and-Play Framework with Outliers Detection
- 6 July 2023
- Published by Elsevier in Applied Mathematical Modelling
- Vol. 123, 197-212
Nonconvex Rician noise removal via convergent plug-and-play framework
- 6 July 2023
- Published by Elsevier in Applied Mathematical Modelling
- Vol. 123, 197-212
Nonconvex Rician noise removal via convergent plug-and-play framework
- 28 March 2023
- Published by Taylor & Francis in Optimization Methods and Software
- Vol. 38 (5) , 861-886
Efficient second-order optimization with predictions in differential games
A growing number of training methods for generative adversarial networks (GANs) are differential games. Different from convex optimization problems on single functions, gradient descent on multiple objectives may not converge to stable fixed points (SFPs). In order to improve learning dynamics in such games, many recently proposed methods utilize the second-order information of the game, such as the Hessian matrix. Unfortunately, these methods often suffer from the enormous computational cost of Hessian, which hinders their further applications. In this paper, we present efficient second-order optimization (ESO), in which only a part of Hessian is updated in each iteration, and the algorithm is derived. Furthermore, we give the local convergence of the method under reasonable assumptions. In order to further speed up the training process of GANs, we propose efficient second-order optimization with predictions (ESOP) using a novel accelerator. Basic experiments show that the proposed learning methods are faster than some state-of-art methods in GANs, while applicable to many other n-player differential games with local convergence guarantee.
- 28 March 2023
- Published by Taylor & Francis in Optimization Methods and Software
- Vol. 38 (5) , 861-886
Efficient second-order optimization with predictions in differential games
A growing number of training methods for generative adversarial networks (GANs) are differential games. Different from convex optimization problems on single functions, gradient descent on multiple objectives may not converge to stable fixed points (SFPs). In order to improve learning dynamics in such games, many recently proposed methods utilize the second-order information of the game, such as the Hessian matrix. Unfortunately, these methods often suffer from the enormous computational cost of Hessian, which hinders their further applications. In this paper, we present efficient second-order optimization (ESO), in which only a part of Hessian is updated in each iteration, and the algorithm is derived. Furthermore, we give the local convergence of the method under reasonable assumptions. In order to further speed up the training process of GANs, we propose efficient second-order optimization with predictions (ESOP) using a novel accelerator. Basic experiments show that the proposed learning methods are faster than some state-of-art methods in GANs, while applicable to many other n-player differential games with local convergence guarantee.
- 7 March 2022
- Published by Taylor & Francis in International Journal of Computer Mathematics
- Vol. 99 (11) , 2250-2271
Flexible parameter selection methods for Rician noise removal with convergence guarantee
Restoring images corrupted by Rician noise is a challenging issue in the field of medical image processing. In the existing variational methods, there is a balancing parameter between the regularization term and the fidelity term. However, it is very hard to find the optimal parameter. In this paper, we study the total variation-based Rician noise removal model with spatially varying parameters. We propose flexible and automatic parameter selection strategies to balance the regularization extent between different kinds of image regions. A modified alternating direction method of multipliers is derived to solve the non-convex model efficiently. Theoretically, we prove that if a selection strategy satisfies some reasonable conditions, the convergence of the proposed algorithm is guaranteed. Numerical results demonstrate that the proposed method with automatic parameter selection can better preserve the structures and fine textures than other closely related methods.
- 7 March 2022
- Published by Taylor & Francis in International Journal of Computer Mathematics
- Vol. 99 (11) , 2250-2271
Flexible parameter selection methods for Rician noise removal with convergence guarantee
Restoring images corrupted by Rician noise is a challenging issue in the field of medical image processing. In the existing variational methods, there is a balancing parameter between the regularization term and the fidelity term. However, it is very hard to find the optimal parameter. In this paper, we study the total variation-based Rician noise removal model with spatially varying parameters. We propose flexible and automatic parameter selection strategies to balance the regularization extent between different kinds of image regions. A modified alternating direction method of multipliers is derived to solve the non-convex model efficiently. Theoretically, we prove that if a selection strategy satisfies some reasonable conditions, the convergence of the proposed algorithm is guaranteed. Numerical results demonstrate that the proposed method with automatic parameter selection can better preserve the structures and fine textures than other closely related methods.