皇冠网投-皇冠网上投注足球-bet365是否合法

信息科學(xué)技術(shù)學(xué)院建院20周年系列:網(wǎng)絡(luò)空間安全學(xué)院學(xué)術(shù)講座(八、九、十、十一)

題目一:Robust Low-Tubal-Rank Tensor Recovery from Binary Measurements

內(nèi)容簡(jiǎn)介:This talk focuses on the recovery of low-tubal-rank tensors from binary measurements based on tensor-tensor product (or t-product) and tensor Singular Value Decomposition (t-SVD). Two types of recovery models are considered, one is the tensor hard singular tube thresholding and the other one is the tensor nuclear norm minimization. In the case no random dither exists in the measurements, our research shows that the direction of tensorwith tubal rank r can be well approximated from  random Gaussian measurements. In the case nonadaptive dither exists in the measurements, it is proved that both the direction and the magnitude of  can be simultaneously recovered. As we will see, under the nonadaptive measurement scheme, the recovery errors of two reconstruction procedures decay at the rate of polynomial of the oversampling factor (m is the random Gaussian measurements). In order to obtain faster decay rate, we introduce a recursive strategy and allow the dithers in quantization to be adaptive to previous measurements for each iterations. Under this quantization scheme, two iterative recovery algorithms are proposed which establish recovery errors decaying at the rate of exponent of the oversampling factor. Numerical experiments on both synthetic and real-world data sets are conducted and demonstrate the validity of our theoretical results and the superiority of our algorithms.

報(bào)告人:西南大學(xué)王建軍教授

報(bào)告人簡(jiǎn)介:博士,三級(jí)教授,博士生導(dǎo)師,重慶市學(xué)術(shù)帶頭人,重慶市創(chuàng)新創(chuàng)業(yè)領(lǐng)軍人才,巴渝學(xué)者特聘教授,重慶工業(yè)與應(yīng)用數(shù)學(xué)學(xué)會(huì)副理事長(zhǎng),CSIAM全國(guó)大數(shù)據(jù)與人工智能專(zhuān)家委員會(huì)委員,美國(guó)數(shù)學(xué)評(píng)論評(píng)論員,曾獲重慶市自然科學(xué)獎(jiǎng)勵(lì)。主要研究方向?yàn)椋焊呔S數(shù)據(jù)建模、機(jī)器學(xué)習(xí)(深度學(xué)習(xí))、數(shù)據(jù)挖掘、壓縮感知、張量分析、函數(shù)逼近論等。在神經(jīng)網(wǎng)絡(luò)(深度學(xué)習(xí))逼近復(fù)雜性和高維數(shù)據(jù)稀疏建模等方面有一定的學(xué)術(shù)積累。主持國(guó)家自然科學(xué)基金5項(xiàng),教育部科學(xué)技術(shù)重點(diǎn)項(xiàng)目1項(xiàng),重慶市自然科學(xué)基金1項(xiàng),主研8項(xiàng)國(guó)家自然、社會(huì)科學(xué)基金;現(xiàn)主持國(guó)家自然科學(xué)基金面上項(xiàng)目2項(xiàng),參與國(guó)家重點(diǎn)基礎(chǔ)研究發(fā)展‘973’計(jì)劃一項(xiàng), 多次出席國(guó)際、國(guó)內(nèi)重要學(xué)術(shù)會(huì)議,并應(yīng)邀做大會(huì)特邀報(bào)告22余次。 已在IEEE Transactions on Pattern Analysis and Machine Intelligence2, IEEE Transactions on Neural Networks and Learning System2),Applied and Computational Harmonic Analysis(2),Inverse Problems, Neural Networks, Signal Processing(2), IEEE Signal Processing letters(2), Journal of Computational and applied mathematics, ICASSP,IET Image processing(2), IET Signal processing(4),中國(guó)科學(xué)(A,F)(4), 數(shù)學(xué)學(xué)報(bào)計(jì)算機(jī)學(xué)報(bào)電子學(xué)報(bào)(3)等知名專(zhuān)業(yè)期刊發(fā)表90余篇學(xué)術(shù)論文,IEEE等系列刊物,National Science Review Signal ProcessingNeural Networks,Pattern Recognization,中國(guó)科學(xué)計(jì)算機(jī)學(xué)報(bào),電子學(xué)報(bào),數(shù)學(xué)學(xué)報(bào)等知名期刊審稿人。

 

題目二:噪聲水平未知的低秩矩陣恢復(fù)

內(nèi)容簡(jiǎn)介:目前,低秩矩陣恢復(fù)依然為非?;钴S的研究課題,被廣泛應(yīng)用于量子層析成像、多任務(wù)學(xué)習(xí)、人臉識(shí)別、傳感器定位、圖像處理、機(jī)器學(xué)習(xí)、目標(biāo)監(jiān)測(cè)等方向和領(lǐng)域。低秩矩陣恢復(fù)往往由于其測(cè)量帶有噪聲,使得問(wèn)題處理變得異常困難。傳統(tǒng)含噪低秩矩陣恢復(fù)一般要求具有噪聲水平的正確估計(jì)這一先驗(yàn)信息,并借助核范數(shù)極小化模型實(shí)現(xiàn)的。然而,現(xiàn)實(shí)中這樣的先驗(yàn)信息在很多情形下是很難獲得或者不可能知道的,如遙感圖像、核磁共振圖像、CT圖像等。本報(bào)告主要對(duì)噪聲水平未知的低秩矩陣恢復(fù)問(wèn)題展開(kāi)探討。

報(bào)告人:北方民族大學(xué)高義教授

報(bào)告人簡(jiǎn)介:博士,教授,碩士研究生導(dǎo)師,英國(guó)林肯大學(xué)訪(fǎng)問(wèn)學(xué)者,現(xiàn)代分析數(shù)學(xué)及其應(yīng)用學(xué)術(shù)委員會(huì)委員?,F(xiàn)任北方民族大學(xué)數(shù)學(xué)與信息科學(xué)學(xué)院副院長(zhǎng)。近5年,主要從事稀疏信息處理中的數(shù)學(xué)理論與方法的研究,在隨機(jī)采樣、稀疏信號(hào)處理、低秩矩陣恢復(fù)等方面取得了一些重要成果,以第一作者在《Signal Processing》《中國(guó)科學(xué):數(shù)學(xué)》等知名期刊發(fā)表了多篇較高質(zhì)量的研究論文。主持完成了寧夏自然科學(xué)基金和國(guó)家民委科研項(xiàng)目各1項(xiàng),參與完成國(guó)家自然科學(xué)基金和歐盟項(xiàng)目各2項(xiàng)?,F(xiàn)主持國(guó)家自然科學(xué)基金、寧夏自然科學(xué)基金、寧夏留學(xué)回國(guó)人員創(chuàng)新研究項(xiàng)目各1項(xiàng)。

 

題目三:Some Issues about Canonical Correlation Analysis and Sketch-based Image Retrieval

內(nèi)容簡(jiǎn)介:典型相關(guān)性分析是用來(lái)探索兩個(gè)多變量(向量)之間的關(guān)聯(lián)關(guān)系的多元統(tǒng)計(jì)分析方法,它已經(jīng)廣泛應(yīng)用于基因序列分析,多視圖學(xué)習(xí),跨語(yǔ)言文本檢索、圖像檢索等領(lǐng)域。本報(bào)告首先研究典型相關(guān)分析,核典型相關(guān)分析和條件核典型相關(guān)分析的一些理論分析和相關(guān)算法,接著介紹最近幾年出現(xiàn)的手繪素描檢索的相關(guān)算法。

報(bào)告人:廣東財(cái)經(jīng)大學(xué)蔡佳教授

報(bào)告人簡(jiǎn)介:博士,廣東財(cái)經(jīng)大學(xué)統(tǒng)計(jì)與數(shù)學(xué)學(xué)院教授,碩士生導(dǎo)師。主要研究方向?yàn)榻y(tǒng)計(jì)機(jī)器學(xué)習(xí),數(shù)據(jù)分析,模式識(shí)別。2009 -2015 年曾數(shù)次訪(fǎng)問(wèn)香港城市大學(xué),2017 2 -20182 月訪(fǎng)問(wèn)紐約州立大學(xué)奧爾巴尼分?!,F(xiàn)為廣東省高等學(xué)校千百十人才培養(yǎng)工程校級(jí)培養(yǎng)對(duì)象,國(guó)家自然科學(xué)基金評(píng)審入庫(kù)專(zhuān)家,教育部科技管理系統(tǒng)入庫(kù)專(zhuān)家,廣東省自然科學(xué)基金評(píng)審專(zhuān)家。擔(dān)任廣東省計(jì)算數(shù)學(xué)學(xué)會(huì)常務(wù)理事,廣東省計(jì)算機(jī)學(xué)會(huì)大數(shù)據(jù)專(zhuān)委會(huì)委員。曾參加第三屆國(guó)際計(jì)算調(diào)和分析會(huì)議(上海), 第四屆數(shù)學(xué)太平洋峰會(huì)(香港), 第七屆曲線(xiàn)和曲面上的數(shù)學(xué)方法會(huì)議(挪威), 第二十五屆國(guó)際機(jī)器學(xué)習(xí)會(huì)議(芬蘭), 計(jì)算學(xué)習(xí)理論和實(shí)踐夏令營(yíng)(美國(guó)),計(jì)算學(xué)習(xí)理論會(huì)議(法國(guó)),歐洲機(jī)器學(xué)習(xí)會(huì)議(德國(guó))等并在會(huì)上作報(bào)告。已在國(guó)內(nèi)外著名期刊《IEEE Transactions on Neural Networks and Learning Systems》,《Neural Networks》,《Neural Computation》,《Journal of Multivariate Analysis》,《Engineering Applications of Artificial Intelligence》,《Neurocomputing,《中國(guó)科學(xué)》(中英文版)發(fā)表SCI檢索論文近20篇,主持和承擔(dān)了國(guó)家自科(青年,面上),國(guó)家社科,教育部人文社科,國(guó)家統(tǒng)計(jì)局,廣東省自科,廣東省教育廳,廣州市科技計(jì)劃等20余項(xiàng)項(xiàng)目。 現(xiàn)為國(guó)外SCI 檢索期刊IEEE Transactions on Neural Networks and Learning Systems, Neural Networks, Pattern Recognition, Engineering Applications of Artificial Intelligence, International Journal of Wavelets Multiresolution and Information Processing,Journal of Statistical Computation and Simulation等期刊的審稿專(zhuān)家。

 

題目四:Nearly Optimal Number of Iterations for Sparse SignalRecovery with Orthogonal Multi-Matching Pursuit

內(nèi)容簡(jiǎn)介:Recovering a $K$-sparse signal $\mathbf{x}$ from linear measurements $\mathbf{y}=\mathbf{A}\mathbf{x}+\mathbf{w}$,where $\mathbf{A}$ is a sensing matrix and $\mathbf{w}$ is a noise vector, arises from numerous applications.

Orthogonal multi-matching pursuit (OMMP), which is an extension of the OMP algorithm, has better recovery performance than OMP. This paper provides a nearly optimal number of iterations for OMMP.Specifically, we show that if the matrix mathbf{A}\in\mathbb{R}^{m\times n}$ satisfies the restricted isometry property (RIP) with $\delta_{6K}\leq0.026$,then OMMP provides a stable reconstruction of  $\mathbf{x}$  in $\lceil\frac{4K}{M}\rceil$iterations, where $M$ is the number of indices chosen in each iteration of the OMMP algorithm.Furthermore, we build an upper bound on the recovery error with fewer required iterations than existing results.

These results show that the required number of iterationsto ensure stable recovery of any $K$-sparse signals are fewer than those required by the start-of-the-art results.

報(bào)告人:河南師范大學(xué)李海鋒副教授

報(bào)告人簡(jiǎn)介:博士。目前在北京應(yīng)用物理與計(jì)算數(shù)學(xué)研究所諶穩(wěn)固老師門(mén)下做博士后研究。主要從事調(diào)和分析、壓縮感知的理論及應(yīng)用研究,在IEEE Journal of Selected Topics in Signal Processing, IEEE Signal Processing Letters, Signal Processing, IET Signal Processing等學(xué)術(shù)刊物發(fā)表科研論文20余篇。

 

時(shí)間:2021411日(周日)下午1430開(kāi)始

地點(diǎn):騰訊會(huì)議ID808 561 189會(huì)議密碼:210410

 

熱烈歡迎廣大師生參加!

 

 

信息科學(xué)技術(shù)學(xué)院

202147