lindermanlab / ssm-jax

Bayesian learning and inference for state space models (SSMs) using Google Research's JAX as a backend
MIT License
58 stars 7 forks source link

Sequential Monte Carlo for generic SSMs #35

Open slinderman opened 2 years ago

slinderman commented 2 years ago

Implement generic SMC algorithm to sample the latent states of a generic SSM. @andrewwarrington already has a working prototype, it just needs to be polished and rolled into main.

See chapter 23.5 of Probabilistic Machine Learning by Murphy (2012).