Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising Priors

Provably Convergent Learned Inexact Descent Algorithm for Low-Dose CT Reconstruction

We propose a provably convergent method, called Efficient Learned Descent Algorithm (ELDA), for low-dose CT (LDCT) reconstruction. ELDA is a highly interpretable neural network architecture with learned parameters and meanwhile retains convergence guarantee as classical optimization algorithms. To improve reconstruction quality, the proposed ELDA also employs a new non-local feature mapping and an associated regularizer. We compare ELDA with several state-of-the-art deep image methods, such as RED-CNN and Learned Primal-Dual, on a set of LDCT reconstruction problems. Numerical experiments demo…

HyDeFuse：可证明收敛的去噪器驱动高光谱融合

HyDeFuse: Provably Convergent Denoiser-Driven Hyperspectral Fusion

本文提出HyDeFuse去噪器驱动的高光谱融合算法，利用伪线性去噪器实现隐式正则化，并通过压缩映射定理证明其全局线性收敛，在公开数据集上验证了融合性能。

用于高光谱异常检测的可证明收敛的即插即用近端点坐标下降法

Provably Convergent Plug-and-play Proximal Block Coordinate Descent Method for Hyperspectral Anomaly Detection

针对高光谱异常检测，提出融合低秩背景表示、隐式近端去噪先验与广义群稀疏的 PnP-PBCD 方法，并证明其收敛性，在含噪与无噪场景下均优于对比方法。

学习弱凸正则化器用于收敛的图像重建算法

Learning Weakly Convex Regularizers for Convergent Image-Reconstruction Algorithms

本文学习具有弱凸模量上界的非凸正则化器，用于变分去噪和可收敛的逆问题重建，以少参数超越凸方法与BM3D，并在CT/MRI中实现性能与可解释性的良好平衡。

一种用于非线性矩阵分解的外推算法及其可证明收敛性

An extrapolated and provably convergent algorithm for nonlinear matrix decomposition with the ReLU function

本文提出了一种用于非线性矩阵分解的外推算法eBCD，证明其收敛性，并展示了其在数据压缩和流形学习中的有效性。

用于收缩图像重建的可训练非扩张去噪器

Trainable Nonexpansive Denoisers for Contractive Image Reconstruction

研究如何训练用于图像重建的去噪器，利用排列对图像格的作用约束神经架构，使其全局非扩张，集成去噪器与成像算子开发出可证明收缩且全局收敛的重建机制，实验表明性能有竞争力且提供Lipschitz保证。