Abstract: Approximate message passing (AMP) algorithms are low-cost iterative algorithms for solving high-dimensional linear regression problems. With independent Gaussian measurements, the performance of AMP can be described by a state evolution recursion in the proportional asymptotic regime. In this talk, we will discuss a variant of AMP based on divergence-free nonlinearities. This algorithm, which we call orthogonal AMP, admits simple state evolution characterization for general rotationally-invariant models, without the need of complicated Onsager correction terms tailored to the matrix spectrum. The simple state evolution structure makes it an appealing template for designing efficient and analyzable algorithms for various signal estimation problems, as we will briefly mention in this talk.
Bio: I received my B.Eng degree from Xidian University, China in 2010, and my Ph.D degree from City University of Hong Kong in 2015. After graduation, I stayed at City University of Hong Kong as a research fellow. I was a postdoctoral researcher at Columbia University from September 2016 to June 2019, and a postdoctoral fellow at Harvard University from July 2019 to June 2020. My research interests include statistical signal processing, message passing algorithms, and optimization.