MLE for partially observed diffusions: Direct maximization vs. the EM algorithm

DOI10.1016/0304-4149(89)90041-0zbMath0709.62076OpenAlexW2087348129MaRDI QIDQ921782

François Le Gland, Fabien Campillo

Publication date: 1989

Published in: Stochastic Processes and their Applications (Search for Journal in Brave)

Full work available at URL: https://hal.inria.fr/inria-00075670/file/RR-0884.pdf

zbMATH Keywords

algorithmsiterative algorithmEM algorithmhidden Markov modelnonlinear filteringmaximum likelihoodconditional expectationsSkorokhod integralnonlinear smoothingNumerical resultsstochastic PDE'sdirect maximizationdiscrete time casepartially observed diffusion processesTime discretization schemes

Mathematics Subject Classification ID

Point estimation (62F10) Markov processes: estimation; hidden Markov models (62M05) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10)

Related Items (13)

Unbiased estimation of the gradient of the log-likelihood for a class of continuous-time state-space models ⋮ Modifications of the EM algorithm for survival influenced by an unobserved stochastic process ⋮ Consistent parameter estimation for partially observed diffusions with small noise ⋮ Stochastic time series with strong, correlated measurement noise: Markov analysis in \(N\) dimensions ⋮ MLE for partially observed diffusions: Direct maximization vs. the EM algorithm ⋮ Erratum: Parameter estimation of partially observed continuous time stochastic processes via the EM algorithm ⋮ Robust parameter estimation for stochastic differential equations ⋮ Maximum Likelihood Estimation in Partially Observed Stochastic Differential System Driven by a Fractional Brownian Motion ⋮ Direct maximization of the likelihood of a hidden Markov model ⋮ Data-Recursive Smoother Formulae for Partially Observed Discrete-Time Markov Chains ⋮ Data-driven modeling of the temporal evolution of breakers' states in the French electrical transmission grid ⋮ Score-Based Parameter Estimation for a Class of Continuous-Time State Space Models ⋮ A Monte Carlo EM Approach for Partially Observable Diffusion Processes: Theory and Applications to Neural Networks

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Probability methods for approximations in stochastic control and for elliptic equations
• MLE for partially observed diffusions: Direct maximization vs. the EM algorithm
• On the convergence properties of the EM algorithm
• A two-sided stochastic integral and its calculus
• Parameter estimation of partially observed continuous time stochastic processes via the EM algorithm
• Stochastic calculus with anticipating integrands
• Stochastic calculus of variations for stochastic partial differential equations
• Consistent parameter estimation for partially observed diffusions with small noise
• Stochastic partial differential equations and filtering of diffusion processes
• Martingales dépendant d'un paramètre: une formule d'Ito
• ON THE CAUCHY PROBLEM FOR LINEAR STOCHASTIC PARTIAL DIFFERENTIAL EQUATIONS
• An Introduction to the Application of the Theory of Probabilistic Functions of a Markov Process to Automatic Speech Recognition

This page was built for publication: MLE for partially observed diffusions: Direct maximization vs. the EM algorithm