Ensemble Kalman Filtering Meets Gaussian Process SSM for Non-Mean-Field and Online Inference

TL;DR

This paper introduces a novel approach combining ensemble Kalman filtering with Gaussian process state-space models to improve online inference and address variational inference challenges under non-mean-field assumptions.

Contribution

The paper proposes integrating EnKF into NMF variational inference for GPSSMs, enabling online learning, reducing parameterization, and providing a closed-form ELBO approximation.

Findings

Enhanced inference accuracy over existing methods

Effective online learning capability demonstrated

Superior performance on real and synthetic datasets

Abstract

The Gaussian process state-space models (GPSSMs) represent a versatile class of data-driven nonlinear dynamical system models. However, the presence of numerous latent variables in GPSSM incurs unresolved issues for existing variational inference approaches, particularly under the more realistic non-mean-field (NMF) assumption, including extensive training effort, compromised inference accuracy, and infeasibility for online applications, among others. In this paper, we tackle these challenges by incorporating the ensemble Kalman filter (EnKF), a well-established model-based filtering technique, into the NMF variational inference framework to approximate the posterior distribution of the latent states. This novel marriage between EnKF and GPSSM not only eliminates the need for extensive parameterization in learning variational distributions, but also enables an interpretable, closed-form approximation of the evidence lower bound (ELBO). Moreover, owing to the streamlined parameterization via the EnKF, the new GPSSM model can be easily accommodated in online learning applications. We demonstrate that the resulting EnKF-aided online algorithm embodies a principled objective function by ensuring data-fitting accuracy while incorporating model regularizations to mitigate overfitting. We also provide detailed analysis and fresh insights for the proposed algorithms. Comprehensive evaluation across diverse real and synthetic datasets corroborates the superior learning and inference performance of our EnKF-aided variational inference algorithms compared to existing methods.