Regime Learning for Differentiable Particle Filters

TL;DR

This paper introduces RLPF, a neural network-based differentiable particle filter that learns multiple regimes and their switching process simultaneously, improving state inference in systems with regime changes.

Contribution

The paper presents a novel RLPF model that jointly learns regimes and switching dynamics, filling a gap in existing differentiable particle filter methods.

Findings

Competitive performance on numerical experiments

Effective learning of regimes and switching process

Advances state inference in regime-switching systems

Abstract

Differentiable particle filters are an emerging class of models that combine sequential Monte Carlo techniques with the flexibility of neural networks to perform state space inference. This paper concerns the case where the system may switch between a finite set of state-space models, i.e. regimes. No prior approaches effectively learn both the individual regimes and the switching process simultaneously. In this paper, we propose the neural network based regime learning differentiable particle filter (RLPF) to address this problem. We further design a training procedure for the RLPF and other related algorithms. We demonstrate competitive performance compared to the previous state-of-the-art algorithms on a pair of numerical experiments.