Variational Inference for Interacting Particle Systems with Discrete Latent States

Abstract

We present a novel Bayesian learning framework for interacting particle systems with discrete latent states, addressing the challenge of inferring dynamics from partial, noisy observations. Our approach learns a variational posterior path measure by parameterizing the generator of the underlying continuous-time Markov chain. We formulate the problem as a multi-marginal Schrödinger bridge with aligned samples, employing a two-stage learning procedure. Our method incorporates an emission distribution for decoding latent states and uses a scalable variational approximation.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Migliorini and Smyth. "Variational Inference for Interacting Particle Systems with Discrete Latent States." NeurIPS 2024 Workshops: BDU, 2024.

Markdown

[Migliorini and Smyth. "Variational Inference for Interacting Particle Systems with Discrete Latent States." NeurIPS 2024 Workshops: BDU, 2024.](https://mlanthology.org/neuripsw/2024/migliorini2024neuripsw-variational/)

BibTeX

@inproceedings{migliorini2024neuripsw-variational,
  title     = {{Variational Inference for Interacting Particle Systems with Discrete Latent States}},
  author    = {Migliorini, Giosue and Smyth, Padhraic},
  booktitle = {NeurIPS 2024 Workshops: BDU},
  year      = {2024},
  url       = {https://mlanthology.org/neuripsw/2024/migliorini2024neuripsw-variational/}
}