English

Differentiable Particle Filtering via Entropy-Regularized Optimal Transport

Machine Learning 2021-07-01 v3 Machine Learning Computation

Abstract

Particle Filtering (PF) methods are an established class of procedures for performing inference in non-linear state-space models. Resampling is a key ingredient of PF, necessary to obtain low variance likelihood and states estimates. However, traditional resampling methods result in PF-based loss functions being non-differentiable with respect to model and PF parameters. In a variational inference context, resampling also yields high variance gradient estimates of the PF-based evidence lower bound. By leveraging optimal transport ideas, we introduce a principled differentiable particle filter and provide convergence results. We demonstrate this novel method on a variety of applications.

Keywords

Cite

@article{arxiv.2102.07850,
  title  = {Differentiable Particle Filtering via Entropy-Regularized Optimal Transport},
  author = {Adrien Corenflos and James Thornton and George Deligiannidis and Arnaud Doucet},
  journal= {arXiv preprint arXiv:2102.07850},
  year   = {2021}
}

Comments

9 pages of content + 11 pages supplementary, accepted for oral at ICML 2021

R2 v1 2026-06-23T23:11:27.982Z