Skip to yearly menu bar Skip to main content


Particle Flow Bayes' Rule

Xinshi Chen · Hanjun Dai · Le Song

Pacific Ballroom #218

Keywords: [ Kernel Methods ] [ Bayesian Deep Learning ] [ Approximate Inference ]


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.

Live content is unavailable. Log in and register to view live content