Particle Flow Bayes’ Rule

Xinshi Chen, Hanjun Dai, Le Song
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:1022-1031, 2019.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-chen19c, title = {Particle Flow {B}ayes’ Rule}, author = {Chen, Xinshi and Dai, Hanjun and Song, Le}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {1022--1031}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/chen19c/chen19c.pdf}, url = {https://proceedings.mlr.press/v97/chen19c.html}, 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.} }
Endnote
%0 Conference Paper %T Particle Flow Bayes’ Rule %A Xinshi Chen %A Hanjun Dai %A Le Song %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-chen19c %I PMLR %P 1022--1031 %U https://proceedings.mlr.press/v97/chen19c.html %V 97 %X 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.
APA
Chen, X., Dai, H. & Song, L.. (2019). Particle Flow Bayes’ Rule. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:1022-1031 Available from https://proceedings.mlr.press/v97/chen19c.html.

Related Material