The Expectation-Maximization (EM) algorithm is an iterative optimization technique that seeks to find the maximum likelihood parameter estimates in problems where some of the data is missing or hidden, or in problems that can be posed in a similar form, such as mixture model parameter estimation. The EM algorithm can be viewed in many different ways, one of the most insightful being in terms of...

Combining a naive Bayes classifier with the EM algorithm is one of the promising approaches for making use of unlabeled data for disambiguation tasks when using local context features including word sense disambiguation and spelling correction. However, the use of unlabeled data via the basic EM algorithm often causes disastrous performance degradation instead of improving classification perfor...

Expectation-maximization (EM) is an iterative algorithm for finding the maximum likelihood or maximum a posteriori estimate of the parameters of a statistical model with latent variables or when we have missing data. In this work, we view EM in a generalized surrogate optimization framework and analyze its convergence rate under commonly-used assumptions. We show a lower bound on the decrease i...

We provide global convergence guarantees for the expectation-maximization (EM) algorithm applied to mixtures of two Gaussians with known covariance matrices. We show that EM converges geometrically to the correct mean vectors, and provide simple, closed-form expressions for the convergence rate. As a simple illustration, we show that in one dimension ten steps of the EM algorithm initialized at...

In this paper we introduce a naive algorithm for nondeterminisctic LTAG derivation tree extraction from the Penn Treebank and the Proposition Bank. This algorithm is used in the EM models of LTAG Treebank Induction reported in (Shen and Joshi, 2004). Given the trees in the Penn Treebank with PropBank tags, this algorithm generates shared structures that allow efficient dynamic programming in th...

OBJECTIVE To improve the quality of expectation maximizing (EM) for brain image segmentation, and to evaluate the accuracy of segmentation results. METHODS This brain segmentation study was conducted in Universiti Putra Malaysia in Serdong, Malaysia between February and November 2010 on simulated and real images using novel improvement for EM. The EM-1 (proposed algorithm) was compared with n...

We develop an EM algorithm for estimating parameters that determine the dynamics of a discrete time Markov chain evolving through a certain measurable state space. As a key tool for the construction of the EM method we develop forward-reverse representations for Markov chains conditioned on a certain terminal state. These representations may be considered as an extension of the earlier work [1]...

Regression mixture models are widely studied in statistics, machine learning and data analysis. Fitting regression mixtures is challenging and is usually performed by maximum likelihood by using the expectation-maximization (EM) algorithm. However, it is well-known that the initialization is crucial for EM. If the initialization is inappropriately performed, the EM algorithm may lead to unsatis...

Factor analysis is a standard tool in educational testing contexts, which can be fit using the EM algorithm (Dempster, Laird and Rubin (1977)). An extension of EM, called the ECME algorithm (Liu and Rubin (1994)), can be used to obtain ML estimates more efficiently in factor analysis models. ECME has an E-step, identical to the E-step of EM, but instead of EM’s M-step, it has a sequence of CM (...

This paper investigates the problem of blindly acquiring the channel gains for a synchronized multiuser system using the expectation maximization (EM) algorithm. The EM algorithm takes advantage of the finite alphabet property of the transmitted signal. It also provides MMSE estimates of the transmitted data that can be used by the receiver for decoding purposes. The algorithm has been applied ...