We propose a linear-mapping based variational Ensemble Kalman filter for sequential Bayesian filtering problems with generic observation models. Specifically, the proposed method is formulated as to construct a linear mapping from the prior ensemble to the posterior one, and the linear mapping is computed via a variational Bayesian formulation, i.e., by minimizing the Kullback-Leibler divergence between the transformed distribution by the linear mapping and the actual posterior. A gradient descent scheme is proposed to solve the resulting optimization problem. With numerical examples we demonstrate that the method has competitive performance against existing methods.

翻译：我们建议用线性图绘制基于线性图谱的以线性图谱的Kalman过滤器来筛选与通用观测模型相继的巴伊西亚过滤问题,具体地说,拟议的方法是设计从先前的组合图到后方图的线性图谱,线性图谱是通过一种变式巴伊西亚配方计算的,即最大限度地缩小线性图与实际的后方图的变形分布之间的Kullback-Libel差。建议了一个梯度下降法,以解决由此产生的优化问题。我们用数字实例表明,该方法与现有方法相比具有竞争性性能。