Academic Report of School of Mathematical Sciences [2026] No. 057

(Series Report for High-Level University Construction No. 1316)

Title：Pretrained Transform-Based Tensor Representations

Speaker：Xile Zhao, Professor (University of Electronic Science and Technology of China)

Time：14:00-15:30, June 12, 2026

Location：Huixing Building Room 702, Yuehai Campus

Abstract: Recently, Fourier transform-based tensor representations have been  suggested for processing and analyzing multi-dimensional data arising from real-world applications, where transform and the corresponding latent tensor serve as the two building blocks of this framework. From both perspectives, this talk will review recent progress in transform-based tensor representations. On one hand, we will discuss the evolution of the transform from linear and shallow ones to nonlinear and deep ones. On the other hand, we will discuss the evolution  of the corresponding latent tensor  from   shallow and untrained ones to deep and pretrained ones Finally, we will also discuss the limitations and future possibilities of the transform-based tensor representation.

Speaker Profile：Xile Zhao is a professor and doctoral advisor at the University of Electronic Science and Technology of China, and Deputy Secretary-General of the Chinese Society for Industrial and Applied Mathematics. He has been selected as a National High-Level Young Talent, a Sichuan Provincial Academic and Technical Leader, and a Sichuan Provincial Outstanding Young Scholar. He has published research as first or corresponding author in prestigious journals such as the SIAM series (SIIMS and SISC), the IEEE series (TPAMI, TIP, TSP, TKDE, etc.), Inverse Problems, and top conferences including CVPR. His research achievements have been recognized with the First Prize in Natural Sciences of Sichuan Province, the First Prize in Scientific and Technological Progress of Sichuan Province, the Second Prize in Natural Sciences of Jiangxi Province, the Huawei Spark Award, and the Huawei Technology Cooperation Achievement Transformation Award. He has led projects funded by the National Natural Science Foundation of China (NSFC), the China-Russia Mathematics Challenge Fund, and Huawei.

Faculty and students are welcome to attend!

Invited by: Xiaoli Zhang

School of Mathematical Sciences

June 11, 2026