Combined Parameter and State Estimation in Simulation-Based Filtering

By Jane Liu, Matthew West. Sequential Monte Carlo Methods in Practice, 2001

1,060 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/a751ba5c04090c565b562b90f8ecee29223eba01

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

Asymptotic efficiency and finite-sample properties of the generalized profiling estimation of parameters in ordinary differential equations (2009, background): “[4]) in the frequentist domain or the Bayesian sequential Monte Carlo (see Liu and West [17]) in the Bayesian domain.”
Truncated Importance Sampling (2008, methodology): “Methods that employ basic sequential Monte Carlo techniques for parameter estimation by judiciously adding stochasticity to the parameters (Liu and West 2001; Ionides et al. 2006) could be applied in situations such as Section 7, and could also potentially benefit from truncation of importance weigh”
Convolution Particle Filter for Parameter Estimation in General State-Space Models (2009, methodology): “To avoid these additions Liu and West [17] propose smoothing the empirical measure of the parameter posterior probability distribution with a Gaussian distribution.”
Particle methods for change detection, system identification, and control (2004, background): “This problem was quickly identified, and in order to limit it, several authors proposed using kernel density estimation methods [25], [39].”
A UNIFIED FRAMEWORK FOR MODELLING WILDLIFE POPULATION DYNAMICS † (2005, methodology): “Auxiliary particle filtering combined with kernel smoothing of parameters was first suggested by Liu & West (2001).”
Monte Carlo State-Space Likelihoods by Weighted Posterior Kernel Density Estimation (2004, methodology): “Another approach by Gilks and Berzuini (2001) and Berzuini and Gilks (2001) is to use MCMC steps to mix particles after each lter step.”
On the utility of graphics cards to perform massively parallel simulation of advanced Monte Carlo methods (2009, methodology): “In such models, all the variances and covariances are modelled through a low dimensional stochastic volatility structure driven by common factors (Liu and West 2000; Pitt and Shephard 1999).”
Plug-and-play inference for disease dynamics: measles in large and small populations as a case study (2009, methodology): “The popularity of the artificial parameter evolution method of Liu & West (2001) may be due more to the convenience of its plug-and-play property than to its statistical properties.”
A Review of Innovation-Based Methods to Jointly Estimate Model and Observation Error Covariance Matrices in Ensemble Data Assimilation (2018, methodology): “The main difference between the four methods comes from the innovations taken into account: the total innovation, as in the EM algorithm proposed by Shumway and Stoffer (1982); lag innovations, following the idea given in Mehra (1970); or different type of innovations in the observation space, as in”
State and parameter estimation of hydrologic models using the constrained ensemble Kalman filter (2009, methodology): “For the treatment of parameter propagation, many methods have been discussed in the literature [e.g., Liu and West, 2001; Anderson, 2001; Evensen, 2006].”
Particle filters for state-space models with the presence of unknown static parameters (2002, background): “[21], and Liu and West [22] introduced diversity in the set of particles by adding random noise to the particles, which in this context is similar to approximate the nondynamic parameters by some”
Online Sparse Multi-Output Gaussian Process Regression and Learning (2019, methodology): “This allows the exploration of the hyperparameter space using the kernel smoothing with shrinkage while yielding converged hyperparameter estimates [58]–[60].”
Statistical Inference for Partially Observed Markov Processes via the R Package pomp (2015, methodology): “This approach has been used in a variety of previously proposed POMP methodologies (Kitagawa 1998; Liu and West 2001; Wan and Merwe 2000) but iterated ﬁltering is distinguished by having theoretical justiﬁcation for convergence to the maximum likelihood estimate (Ionides et al. 2011).”