viking_kalman: Variational Bayesian Variance Tracking in Python, a fast implementation of the R viking package

arXiv (Cornell University) 2026 Preprint Open access

Read full text
Authors: Yann Allioux, Hamadieh, Athir, Viennot, Louis, El Azzaoui, Ismaïl, Gourbilleau, Antoine, Joseph de Vilmarest
DOI: 10.5281/zenodo.20171756
Cited by: 0

Abstract

viking_kalman is a high-performance Python port of the original R package viking. It provides a state-of-the-art Variational Bayesian (VIKING) approach to track the evolution of state and observation noise variances in state-space models. This project is a reimplementation and extension of the research by Joseph de Vilmarest. It includes a scikit-learn-style API, optimized C-extensions for grid search, and built-in diagnostic tools for Kalman filtering and smoothing.

Fields of Study & Subjects

Target Tracking and Data Fusion in Sensor Networks Control Systems and Identification Fault Detection and Control Systems

Publication details

Journal / source
arXiv (Cornell University)
Publication date
11 May 2026
Language
EN
Document type
Preprint