arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.00640cs.LGstat.ML
收藏

粒子流贝叶斯规则

Particle Flow Bayes' Rule

Georgia Institute of Technology(佐治亚理工学院);Ant Financial(蚂蚁金服)

Xinshi Chen, Hanjun Dai, Le Song

摘要:

我们提出了一个粒子流实现贝叶斯规则,其中一个基于ODE的神经操作符被用来传输粒子从一个新的观察后,其前后。我们证明了这样一个ODE算子存在。它的神经参数化可以在元学习框架中进行训练,允许该操作员推理个体观察对后验的影响,从而在不同的先验、观察和顺序贝叶斯推理中进行推广。我们证明了我们的粒子流贝叶斯算子的推广能力,在几个典型的和高维的例子。

英文摘要:

We present a particle flow realization of Bayes' rule, where an ODE-based neural operator is used to transport particles from a prior to its posterior after a new observation. We prove that such an ODE operator exists. Its neural parameterization can be trained in a meta-learning framework, allowing this operator to reason about the effect of an individual observation on the posterior, and thus generalize across different priors, observations and to sequential Bayesian inference. We demonstrated the generalization ability of our particle flow Bayes operator in several canonical and high dimensional examples.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑