Structured Inference Networks for Nonlinear State Space Models

Code

• github.com/clinicalml/structuredinference
  OfficialIn papernone★ 0
• github.com/Salazar-99/Learning-State-Space-Models
  tf★ 0
• github.com/yjlolo/pytorch-deep-markov-model
  pytorch★ 0

Abstract

Gaussian state space models have been used for decades as generative models of sequential data. They admit an intuitive probabilistic interpretation, have a simple functional form, and enjoy widespread adoption. We introduce a unified algorithm to efficiently learn a broad class of linear and non-linear state space models, including variants where the emission and transition distributions are modeled by deep neural networks. Our learning algorithm simultaneously learns a compiled inference network and the generative model, leveraging a structured variational approximation parameterized by recurrent neural networks to mimic the posterior distribution. We apply the learning algorithm to both synthetic and real-world datasets, demonstrating its scalability and versatility. We find that using the structured approximation to the posterior results in models with significantly higher held-out likelihood.

Tasks

Benchmark Results

Reproductions