Colloquium | |
DATE | 2020-09-24 16:10-17:00 |
PLACE | 數學館3174教室 |
SPEAKER | 李彥寰 教授(臺灣大學資訊工程學系) |
TITLE | Non-Asymptotic Analysis of EM in Poisson Inverse Problems |
ABSTRACT |
Poisson inverse problems arise in many real-world applications, such as positron emission tomography and astronomical image deblurring. Expectation maximization (EM) is a standard---and perhaps the most popular---approach to solving a Poisson inverse problem. Vardi et al. proved EM asymptotically converges more than three decades ago; however, it was unclear how fast EM converges. In this talk, I will present a non-asymptotic convergence guarantee for EM. Our analysis exploits an interesting connection between EM and a portfolio selection method due to Cover. 學者簡介 |