Aug 17, 2021 03:00 PM Singapore (Registration will open at 02:50 PM.)
Join Zoom Meeting:
Meeting ID: 980 2457 5137
Learning sparse representations for data is a fundamental task in many signal processing applications. In many domains, we frequently encounter datasets where some intrinsic form of symmetry or invariance is observed. As such, it is natural to consider learning data representations that respect such symmetries. In this talk, I will describe a framework for learning sparse representations for data under the constraint that these symmetries or invariances are respected. In particular, the framework extends the ideas of Convolutional Dictionary Learning to symmetries beyond discrete shifts. The framework builds on ideas from convex geometry and group representation theory; in particular, it exploits a very interesting connection between semidefinite representations and trigonometric polynomials.
Joint work with Z. Feng, S. Ghosh, and A. Low
The paper can be found at: https://arxiv.org/abs/2007.07550
Yong Sheng Soh is an Assistant Professor in the Department of Mathematics at the National University of Singapore. He holds a concurrent appointment as a Research Scientist at the Institute of High Performance Computing, Singapore. He received his Ph.D. in Applied and Computational Mathematics from Caltech (2018) and his B.A. in Mathematics from the University of Cambridge (2011). He was awarded the W.P. Carey & Co. Prize for the best doctoral thesis in Applied Mathematics, the Ben P.C. Chou Prize for the best doctoral thesis in Information Science and Technology, and the 2018 INFORMS Optimization Society Student Paper Prize. His research interests are in mathematical optimization with a focus on applications in the data sciences.
For more information about the ESD Seminar, please email email@example.com