06-30 讲座预告:函数型数据分析

发布时间:2023-06-29

 

题目一:函数型数据分析

内容简介:介绍函数型数据分析,指出其与多元数据分析相比所具有的优势。进一步介绍函数型数据分析的一些重要方法,包括均值函数、协方差函数的估计,函数型预测等。

报告人:陈迪荣

报告人简介:北京航空航天大学数学科学学院教授,博士生导师。19821月获学士学位(华中师范大学),19927月获博士学位(北京师范大学)。先后从事函数逼近论、小波分析、统计学习理论和函数型数据分析方向研究,取得了具有国际先进水平的成果。先后主持国家自然科学基金8项,“863”课题3项,“973”计划子课题1项,航天应用数学基金1项。发表SCI论文80篇,其中多篇发表在权威刊物Appl. Comput. Harmon. Anal.Found. Comput. Math. SIAM J. Math. Anal.SIAM J. Numer. Anal.IEEE Trans. Automat. ControlIEEE Trans. Inform. TheoryJ. Mach. Learn. Res.等上,单篇论文被SCI引用最高200次。获教育部自然科学二等奖、北京市教学成果一等奖。曾获聘北航蓝天学者特聘教授(2006年),获北航立德树人卓越奖(2022年)。迄今为止,先后担任三届校学术委员会委员。

 

题目二:Low tubal rank tensor sensing and robust PCA from quantized measurements

内容简介:Low-rank tensor Sensing (LRTS) is a natural extension of low-rank matrix Sensing (LRMS) to high-dimensional arrays, which aims to reconstruct an underlying tensor X from incomplete linear measurements M(X). However, LRTS ignores the error caused by quantization, limiting its application when the quantization is low-level. Under the tensor Singular Value Decomposition (t-SVD) framework, two recovery methods are proposed. These methods can recover a real tensor X with tubal rank r from m random Gaussian binary measurements with errors decaying at a polynomial speed of the oversampling factor. To improve the convergence rate, we develop a new quantization scheme under which the convergence rate can be accelerated to an exponential function of lambda. Quantized Tensor Robust Principal Component Analysis (Q-TRPCA) aims to recover a low-rank tensor and a sparse tensor from noisy, quantized, and sparsely corrupted measurements Anonconvex constrained maximum likelihood (ML) estimation method is proposed for Q-TRPCA. We provide an upper bound on the Frobenius norm of tensor estimation error under this method. Making use of tools in information theory, we derive a theoretical lower bound on the best achievable estimation error from unquantized measurements. Compared with the lower bound, the upper bound on the estimation error is nearly order-optimal. We further develop an efficient convex ML estimation scheme for Q-TRPCA based on the tensor nuclear norm (TNN) constraint. This method is more robust to sparse noises than the latter nonconvex ML estimation approach. Numerical experiments verify our results, and the applications to real-world data demonstrate the promising performance of the proposed methods.

报告人:王建军

报告人简介:博士,三级教授,博士生导师,重庆市学术技术带头人,重庆市创新创业领军人才,巴渝学者特聘教授,重庆市工业与应用数学学会副理事长,重庆市运筹学会副理事长,美国数学评论评论员,重庆数学会常务理事,曾获重庆市自然科学奖,主要研究方向为:高维数据建模、压缩感知、低秩张量分析、神经网络与函数逼近等。在神经网络逼近复杂性和稀疏逼近等方面有较好的学术积累。已在IEEE TPAMI5),IEEE TITIEEE TIPIEEE TNNLS3),ACHA2),IPPR, KBS, AAAIIEEE SPL(3), SP3),NNICASSP(5), 中国科学(5, 计算机学报,数学学报,电子学报(3)等国内外顶级学术期刊发表90余篇学术论文,授权发明专利1项。主持国家自然科学基金5项, 应邀做大会特邀报告30余次。

 

  间:2023630日(周五)上午 930

  点:腾讯会议:196-505-349

 

热烈欢迎广大师生参加!

 

 

网络空间安全学院

2023629