adv

adv

Dimension-free Wasserstein contraction for nonlinear filters. (arXiv:1708.01582v1 [math.ST])

For a class of partially observed diffusions, sufficient conditions are given for the map from initial condition of the signal to filtering distribution to be contractive with respect to Wasserstein distances, with rate which has no dependence on the dimension of the state-space and is stable under tensor products of the model. The main assumptions are that the signal has affine drift and constant diffusion coefficient, and that the likelihood functions are log-concave. Contraction estimates are obtained from an $h$-process representation of the transition probabilities of the signal reweighted so as to condition on the observations.查看全文

Solidot 文章翻译

你的名字

留空匿名提交
你的Email或网站

用户可以联系你
标题

简单描述
内容