End-to-End Learning of Gaussian Mixture Proposals Using Differentiable Particle Filters and Neural Networks

Benjamin Cox; Sara Pérez-Vieites; Nicolas Zilberstein; Martin Sevilla; Santiago Segarra; Víctor Elvira

ICASSP 2024accepted0 citations

End-to-End Learning of Gaussian Mixture Proposals Using Differentiable Particle Filters and Neural Networks

Benjamin Cox, Sara Pérez-Vieites, Nicolas Zilberstein, Martin Sevilla, Santiago Segarra, Víctor Elvira

Abstract

We introduce a new method, named PropMixNN, that uses a neural network to learn the proposal distribution of a particle filter. The optimal proposal distribution is approximated as a multivariate Gaussian mixture, so the proposed method aims at learning the means and covariance matrices of the S components that characterise the mixture. This unsupervised method is trained to target the log-likelihood, which does not require knowledge of the hidden state. The performance of the method is assessed in a stochastic Lorenz 96 model, which presents a non-linear chaotic behaviour. The proposed method reduces estimation errors in comparison with the state-of-the-art, showing greater improvement in highly non-linear scenarios.

BibTeX

@inproceedings{icassp2024_endtoendlearning,
  title = {End-to-End Learning of Gaussian Mixture Proposals Using Differentiable Particle Filters and Neural Networks},
  author = {Benjamin Cox and Sara Pérez-Vieites and Nicolas Zilberstein and Martin Sevilla and Santiago Segarra and Víctor Elvira},
  booktitle = {ICASSP 2024},
  year = {2024}
}