Score-Based Parameter Estimation for a Class of Continuous-Time State Space Models

DOI10.1137/20M1362942OpenAlexW3183403283MaRDI QIDQ5005015

Alexandros Beskos, Nikolas Kantas, Hamza M. Ruzayqat, Ajay Jasra, Dan Crisan

Publication date: 4 August 2021

Published in: SIAM Journal on Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2008.07803

zbMATH Keywords

parameter estimationparticle filterscore functiondiffusion bridges

Mathematics Subject Classification ID

Numerical methods (including Monte Carlo methods) (91G60) Monte Carlo methods (65C05) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Brownian motion (60J65) Signal detection and filtering (aspects of stochastic processes) (60G35) Diffusion processes (60J60) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35) Stochastic particle methods (65C35)

Related Items (4)

Unbiased estimation of the gradient of the log-likelihood for a class of continuous-time state-space models ⋮ Multilevel estimation of normalization constants using ensemble Kalman-Bucy filters ⋮ Continuous-discrete smoothing of diffusions ⋮ Joint Online Parameter Estimation and Optimal Sensor Placement for the Partially Observed Stochastic Advection-Diffusion Equation

Uses Software

• Bridge.jl
• BayesEstDiffusion.jl

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Particle approximations of the score and observed information matrix in state space models with application to parameter estimation
• Multilevel Monte Carlo methods and applications to elliptic PDEs with random coefficients
• Efficient particle-based online smoothing in general hidden Markov models: the PaRIS algorithm
• MLE for partially observed diffusions: Direct maximization vs. the EM algorithm
• Fundamentals of stochastic filtering
• On coupling particle filter trajectories
• Improved bridge constructs for stochastic differential equations
• Particle methods for stochastic differential equation mixed effects models
• Multilevel particle filters for the non-linear filtering problem in continuous time
• Bayesian estimation of discretely observed multi-dimensional diffusion processes using guided proposals
• Guided proposals for simulating multi-dimensional diffusion bridges
• Application of Girsanov theorem to particle filtering of discretely observed continuous-time non-linear systems
• Simulation of elliptic and hypo-elliptic conditional diffusions
• Exact and Computationally Efficient Likelihood-Based Estimation for Discretely Observed Diffusion Processes (with Discussion)
• Multilevel Particle Filters
• References
• A backward particle interpretation of Feynman-Kac formulae
• Central limit theorems for coupled particle filters
• Online Maximum-Likelihood Estimation of the Parameters of Partially Observed Diffusion Processes

This page was built for publication: Score-Based Parameter Estimation for a Class of Continuous-Time State Space Models