The EM algorithm and extensions

By Geoffrey J. McLachlan, T. Krishnan. 1996

How researchers see this paper

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

Citations in the corpus

Learning and Refining of Privileged Information-Based RNNs for Action Recognition from Depth Sequences (2017, methodology): “Apart from optimizing network parameters, the bridging matrix of modeling latent PI can be updated iteratively by a closed-form solution in the M-step of EM procedure [31, 36, 3]:”
Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning (2020, methodology): “derlying the data, which is assumed to be i:i:d. Existing density estimation algorithms can be divided into two categories: (a) parametric or semiparametric approaches such as Gaussian Mixture models [57,1,16,40,90] and probabilistic graphical models [25,29,87]; and (b) non-parametric approaches suc”
Maximum Likelihood Estimation of VARMA Models Using a State‐Space EM Algorithm (2007, methodology): “Therefore, each iteration of the algorithm increases l(h|Yn) and, if l(h|Yn) is bounded from above, l(h (i)|Yn) converges to a stationary value of l(h|Yn) (conditions of Wu, 1983, summarized in Krishnan and McLachlan, 1997, Sect.”
Computational cluster validation in post-genomic data analysis (2005, methodology): “Clustering can also be applied directly to sequence the data, for example to group genes based on shared cis - regulatory regions (Bilu and Linial, 2002).”
Analysis of isothermal remanent magnetization acquisition curves using the expectation-maximization algorithm (2002, methodology): “We have not included a formal derivation of the EM algorithm, because the essential information on the algorithm and its application to finite mixture models can be found in Dempster et al. (1977); Jones & McLachlan (1990); McLachlan & Krishnan (1997) and McLachlan & Peel (2000).”
Learning Occupancy Grid Maps with Forward Sensor Models (2003, unknown): “EM is an iterative algorithm that gradually maximizes the expected log-likelihood (McLachlan and Krishnan, 1997; Neal and Hinton, 1998).”
A mixture of experts model for rank data with applications in election studies (2008, methodology): “Subsequent to convergence, approximate standard errors of the MLEs were calculated as detailed in McLachlan and Krishnan (1997) and McLachlan and Peel (2000).”
Sparse Methods for Direction-of-Arrival Estimation (2016, methodology): “To optimize (31), an expectation-maximization (EM) algorithm is adopted [64].”
Probabilistic Inductive Logic Programming (2004, methodology): “It is a numerical optimization problem, and all known algorithms involve nonlinear optimization The most commonly adapted technique for probabilistic logic learning is the Expectation-Maximization (EM) algorithm [10, 28].”
The Weibull-geometric distribution (2008, methodology): “We use the EM algorithm 7 8 to obtain <inline-graphic xmlns:xlink="http://www.”
Experimental study on prototype optimisation algorithms for prototype-based classification in vector spaces (2006, methodology): “The standard method used to fit finite mixture models to the observed data, hence to estimate the parameters of the class distributions, is the well-known EM algorithm [27,28].”