Particle Flow Bayes' Rule
arXiv:1902.00640
Abstract
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.
References in corpus (9)
- Learning Combinatorial Optimization Algorithms over Graphs
- Neural Ordinary Differential Equations
- FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
- Nonparametric variational inference
- Provable Bayesian Inference via Particle Mirror Descent
- Monge-Ampère Flow for Generative Modeling
- Stochastic Variational Inference
- A Geometric View of Optimal Transportation and Generative Model
- Filtering with State-Observation Examples via Kernel Monte Carlo Filter