Non-Gaussian Bayesian Filtering
组织者
演讲者
孙泽钜
时间
2022年10月20日 20:00 至 20:30
地点
Online
摘要
In this talk, I will introduce a method of parametrizing the state process of a filtering problem by power moments. The parameters of the proposed parametrization can be determined by a convex optimization scheme with moments constraints, to which the solution is proved to exist and be unique. I will also discuss the necessary and sufficient condition for all the power moments of the density estimate to exist and be finite, as well as the error upper bounds of the density estimate. The contents of this talk are based on the paper entitled Non-Gaussian Bayesian Filtering by Density Parametrization Using Power Moments, arXiv:2207.08519.