Recursive Bayesian Decoding in State Observation Models: Theory and Application in Quantum-Based Inference

Accurately estimating a sequence of latent variables in state observation models remains a challenging problem, particularly when maintaining coherence among consecutive estimates. While forward filtering and smoothing methods provide coherent marginal distributions, they often fail to maintain cohe...

Full description

Saved in:
Bibliographic Details
Main Authors: Branislav Rudić, Markus Pichler-Scheder, Dmitry Efrosinin
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/12/2012
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432284174745600
author Branislav Rudić
Markus Pichler-Scheder
Dmitry Efrosinin
author_facet Branislav Rudić
Markus Pichler-Scheder
Dmitry Efrosinin
author_sort Branislav Rudić
collection DOAJ
description Accurately estimating a sequence of latent variables in state observation models remains a challenging problem, particularly when maintaining coherence among consecutive estimates. While forward filtering and smoothing methods provide coherent marginal distributions, they often fail to maintain coherence in marginal MAP estimates. Existing methods efficiently handle discrete-state or Gaussian models. However, general models remain challenging. Recently, a recursive Bayesian decoder has been discussed, which effectively infers coherent state estimates in a wide range of models, including Gaussian and Gaussian mixture models. In this work, we analyze the theoretical properties and implications of this method, drawing connections to classical inference frameworks. The versatile applicability of mixture models and the prevailing advantage of the recursive Bayesian decoding method are demonstrated using the double-slit experiment. Rather than inferring the state of a quantum particle itself, we utilize interference patterns from the slit experiments to decode the movement of a non-stationary particle detector. Our findings indicate that, by appropriate modeling and inference, the fundamental uncertainty associated with quantum objects can be leveraged to decrease the induced uncertainty of states associated with classical objects. We thoroughly discuss the interpretability of the simulation results from multiple perspectives.
format Article
id doaj-art-23cedb7b3cf4446bb4dee9b80c541d30
institution Kabale University
issn 2227-7390
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-23cedb7b3cf4446bb4dee9b80c541d302025-08-20T03:27:24ZengMDPI AGMathematics2227-73902025-06-011312201210.3390/math13122012Recursive Bayesian Decoding in State Observation Models: Theory and Application in Quantum-Based InferenceBranislav Rudić0Markus Pichler-Scheder1Dmitry Efrosinin2Linz Center of Mechatronics GmbH, 4040 Linz, AustriaLinz Center of Mechatronics GmbH, 4040 Linz, AustriaInstitute of Stochastics, Johannes Kepler University, 4040 Linz, AustriaAccurately estimating a sequence of latent variables in state observation models remains a challenging problem, particularly when maintaining coherence among consecutive estimates. While forward filtering and smoothing methods provide coherent marginal distributions, they often fail to maintain coherence in marginal MAP estimates. Existing methods efficiently handle discrete-state or Gaussian models. However, general models remain challenging. Recently, a recursive Bayesian decoder has been discussed, which effectively infers coherent state estimates in a wide range of models, including Gaussian and Gaussian mixture models. In this work, we analyze the theoretical properties and implications of this method, drawing connections to classical inference frameworks. The versatile applicability of mixture models and the prevailing advantage of the recursive Bayesian decoding method are demonstrated using the double-slit experiment. Rather than inferring the state of a quantum particle itself, we utilize interference patterns from the slit experiments to decode the movement of a non-stationary particle detector. Our findings indicate that, by appropriate modeling and inference, the fundamental uncertainty associated with quantum objects can be leveraged to decrease the induced uncertainty of states associated with classical objects. We thoroughly discuss the interpretability of the simulation results from multiple perspectives.https://www.mdpi.com/2227-7390/13/12/2012Bayesian inferencerecursive estimationdecodingstate observation modeldynamic systemsGaussian mixtures
spellingShingle Branislav Rudić
Markus Pichler-Scheder
Dmitry Efrosinin
Recursive Bayesian Decoding in State Observation Models: Theory and Application in Quantum-Based Inference
Mathematics
Bayesian inference
recursive estimation
decoding
state observation model
dynamic systems
Gaussian mixtures
title Recursive Bayesian Decoding in State Observation Models: Theory and Application in Quantum-Based Inference
title_full Recursive Bayesian Decoding in State Observation Models: Theory and Application in Quantum-Based Inference
title_fullStr Recursive Bayesian Decoding in State Observation Models: Theory and Application in Quantum-Based Inference
title_full_unstemmed Recursive Bayesian Decoding in State Observation Models: Theory and Application in Quantum-Based Inference
title_short Recursive Bayesian Decoding in State Observation Models: Theory and Application in Quantum-Based Inference
title_sort recursive bayesian decoding in state observation models theory and application in quantum based inference
topic Bayesian inference
recursive estimation
decoding
state observation model
dynamic systems
Gaussian mixtures
url https://www.mdpi.com/2227-7390/13/12/2012
work_keys_str_mv AT branislavrudic recursivebayesiandecodinginstateobservationmodelstheoryandapplicationinquantumbasedinference
AT markuspichlerscheder recursivebayesiandecodinginstateobservationmodelstheoryandapplicationinquantumbasedinference
AT dmitryefrosinin recursivebayesiandecodinginstateobservationmodelstheoryandapplicationinquantumbasedinference