Structured Temporal Inference in State-Space Models

Hamidreza Hashempoor

Abstract:

We propose a framework for structured temporal inference in nonlinear state-space
models (SSMs) with hybrid latent dynamics that mix discrete and continuous variables.
Our method follows a two-stage inference: continuous states are estimated via
Kalman inspired updates, while discrete variables are sampled by a neural model
conditioned on these states, avoiding explicit Markov assumptions. To handle
instabilities arising from recurrent dynamics, we introduce stabilization
approach, and train all components jointly using surrogate gradient estimators
that support REINFORCE-style updates.
This design achieves SOTA results across synthetic and real-world datasets,
in state estimation, regime detection, and imputation under noise and
partial observability.

Submission Number: 1155