Mitigating Model Misspecification with Variational Bayesian Inference

Learning dynamical systems from data is an important modelling problem in which one approximates the underlying equations of motion governing the evolution of some system. The conventional approach involves utilising a dynamical model, often derived from expert knowledge to accurately replicate the...

Full description

Bibliographic Details
Main Author: Krissaane, Ines
Format: Thesis (University of Nottingham only)
Language:English
Published: 2024
Subjects:
Online Access:https://eprints.nottingham.ac.uk/79405/
_version_ 1848801115087306752
author Krissaane, Ines
author_facet Krissaane, Ines
author_sort Krissaane, Ines
building Nottingham Research Data Repository
collection Online Access
description Learning dynamical systems from data is an important modelling problem in which one approximates the underlying equations of motion governing the evolution of some system. The conventional approach involves utilising a dynamical model, often derived from expert knowledge to accurately replicate the real-world data. This system often involves the inference of interpretable parameters so that model predictions align with observed data. When a chosen model fails to adequately represent the entire unknown dynamic, the ability to extract meaningful information from a fitted model can be challenging. This thesis investigates strategies addressing dynamical model misspecification within the framework of Bayesian inference. We delve into the limitations of standard Bayesian inference methods, specifically for parameter estimation, uncertainty quantification, and prediction accuracy. In our pursuit of a robust inferential approach, we assess the effectiveness of various contemporary methods such as generalised variational methods for dynamic modelling. Additionally, we introduce novel strategies to address model discrepancy, employing both Gaussian Processes and Approximate Bayesian Computation methods. This research aims to advance our understanding of Bayesian inference under model misspecification and offers practical guidance on constructing robust inferential approaches for more accurate and reliable results in continuous-time dynamic process.
first_indexed 2025-11-14T21:02:19Z
format Thesis (University of Nottingham only)
id nottingham-79405
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T21:02:19Z
publishDate 2024
recordtype eprints
repository_type Digital Repository
spelling nottingham-794052024-12-13T04:40:15Z https://eprints.nottingham.ac.uk/79405/ Mitigating Model Misspecification with Variational Bayesian Inference Krissaane, Ines Learning dynamical systems from data is an important modelling problem in which one approximates the underlying equations of motion governing the evolution of some system. The conventional approach involves utilising a dynamical model, often derived from expert knowledge to accurately replicate the real-world data. This system often involves the inference of interpretable parameters so that model predictions align with observed data. When a chosen model fails to adequately represent the entire unknown dynamic, the ability to extract meaningful information from a fitted model can be challenging. This thesis investigates strategies addressing dynamical model misspecification within the framework of Bayesian inference. We delve into the limitations of standard Bayesian inference methods, specifically for parameter estimation, uncertainty quantification, and prediction accuracy. In our pursuit of a robust inferential approach, we assess the effectiveness of various contemporary methods such as generalised variational methods for dynamic modelling. Additionally, we introduce novel strategies to address model discrepancy, employing both Gaussian Processes and Approximate Bayesian Computation methods. This research aims to advance our understanding of Bayesian inference under model misspecification and offers practical guidance on constructing robust inferential approaches for more accurate and reliable results in continuous-time dynamic process. 2024-12-13 Thesis (University of Nottingham only) NonPeerReviewed application/pdf en cc_by https://eprints.nottingham.ac.uk/79405/1/Mitigating_Model_Misspecification_with_Variational_Bayesian_Inference.pdf Krissaane, Ines (2024) Mitigating Model Misspecification with Variational Bayesian Inference. PhD thesis, University of Nottingham. Model Misspecification Generalised Variational Inference dynamic modelling Bayesian statisics
spellingShingle Model Misspecification
Generalised Variational Inference
dynamic modelling
Bayesian statisics
Krissaane, Ines
Mitigating Model Misspecification with Variational Bayesian Inference
title Mitigating Model Misspecification with Variational Bayesian Inference
title_full Mitigating Model Misspecification with Variational Bayesian Inference
title_fullStr Mitigating Model Misspecification with Variational Bayesian Inference
title_full_unstemmed Mitigating Model Misspecification with Variational Bayesian Inference
title_short Mitigating Model Misspecification with Variational Bayesian Inference
title_sort mitigating model misspecification with variational bayesian inference
topic Model Misspecification
Generalised Variational Inference
dynamic modelling
Bayesian statisics
url https://eprints.nottingham.ac.uk/79405/