报告题目: 稳健单比特压缩感知

报告人: 李晓鹏 助理教授 深圳大学

报告时间: 2024年7月27日（星期六）下午14:30-15:00

报告地点:文理楼290

报告人简介:李晓鹏于2015年获得燕山大学电子科学与技术学士学位，然后分别于2018和2022年获得香港城市大学电子信息工程硕士学位和电气工程博士学位。2018年至2019年，他在深圳大学信息工程系担任研究助理；2022年至2023年在香港城市大学电气工程系担任博士后研究员。目前，他是深圳大学电子与信息工程学院的助理教授。他的研究兴趣包括优化方法、机器学习、稀疏恢复、矩阵处理和张量处理，其应用领域包括目标估计、图像恢复、视频修复、高光谱解混和股票市场分析。发表包括国际权威刊物IEEE T-SP、IEEE T-NNLS、IEEE T-CYB、IEEE T-CSVT等SCI/EI论文30余篇。获国家发明专利授权3项，美国专利授权1项。主持广东省教育厅青年创新人才项目。

报告摘要: One-bit compressed sensing (1-bit CS) inherits the merits of traditional CS and further reduces the cost and burden on the hardware device via employing the 1-bit analog-to-digital converter. When the measurements do not involve sign flips caused by additive noise, most contemporary algorithms can attain excellent signal restoration. However, their recovery performance might significantly degrade if there is even a small portion of sign flips. In order to increase the estimation accuracy in noisy scenarios, we devise a new signal model for 1-bit CS to attain robustness against sign flips. Then, we give a double-sparsity optimization formulation of the restoration problem. Subsequently, we combine proximal alternating minimization and projected gradient descent to tackle the problem. Different from existing robust methodologies, our approach, referred to as robust one-bit CS (ROCS), does not require the number of sign flips. Furthermore, we analyze the convergence behavior of ROCS and show that the objective value and variable sequences converge. Numerical results using synthetic data demonstrate that ROCS is superior to the competing methods in terms of reconstruction error in noisy environments.