報(bào)告題目: A ReLU-based Hard-thresholding Algorithm for Non-negative Sparse Signal Recovery

報(bào)告時(shí)間：2023年5月15日，9：00-10：00

報(bào)告地點(diǎn)：kaiyun開(kāi)云官方網(wǎng)站犀浦校區(qū)7510

報(bào)告人：溫金明（暨南大學(xué)）

摘要：In numerous applications, such as DNA microarrays, face recognition and spectral unmixing,we need to acquire a non-negative K-sparse signal x from an underdetermined linear model y= Ax+v.To recover such sparse signals, we propose a ReLU-based hard-thresholding algorithm (RHT) and then develop two sufficient conditions of stable recovery with RHT, which are respectively based on the restricted isometry property (RIP) and mutual coherence of the sensing matrix A.As far as we know, these two sufficient conditions are the best for hard-thresholding-type algorithms. Finally, we perform extensive numerical experiments to show that RHT has better overall recovery performance and more efficient than the non-negative least squares (NNLS) algorithm,some hard-thresholding-type algorithms including the iterative hard-thresholding (IHT) algorithm, hard-thresholding pursuit (HTP),Newton-step-based iterative hard-thresholding algorithm (NSIHT) and Newton-step-based hard-thresholding pursuit (NSHTP), and Non-Negative orthogonal matching pursuit (NNOMP), Fast NNOMP (FNNOMP) and Support-Shrinkage NNOMP (SNNOMP),which are variants of orthogonal matching pursuit (OMP) for recovering non-negative sparse signals.

報(bào)告人簡(jiǎn)介：溫金明，暨南大學(xué)教授、博導(dǎo)、國(guó)家高層次青年人才、廣東省青年珠江學(xué)者，主持國(guó)家自然科學(xué)基金面上項(xiàng)目2項(xiàng)，省級(jí)項(xiàng)目4項(xiàng)；2015年6月博士畢業(yè)于加拿大麥吉爾大學(xué)數(shù)學(xué)與統(tǒng)計(jì)學(xué)院。從2015年3月到2018年9月，溫教授先后在法國(guó)科學(xué)院里昂并行計(jì)算實(shí)驗(yàn)室、加拿大阿爾伯塔大學(xué)、多倫多大學(xué)從事博士后研究工作。溫教授的研究方向是整數(shù)信號(hào)和稀疏信號(hào)恢復(fù)的算法設(shè)計(jì)與理論分析，以第一作者/通訊作者在Applied and Computational Harmonic Analysis、IEEE Transactions on Information Theory、 IEEE Transactions on Signal Processing等期刊和會(huì)議發(fā)表50余篇學(xué)術(shù)論文。