An optimization algorithm often used for maximum-likelihood estimation in the presence of missing data.
2
votes
2answers
68 views
How to compute expectation for poisson distributed variable in context of binomial?
I'm working on a problem that needs to be solved using EM algorithm. In doing that, I have to evaluate an expectation that I actually have no idea how to.
Consider: $Y$ as a a fixed observed integer ...
0
votes
0answers
15 views
EM soft clustering in lingpipe
In Lingpipe's EM tutorial they said that it is possible to run the algorithm with no supervised data:
It is possible to train a classifier in a completely unsupervised fashion by having the ...
0
votes
1answer
31 views
Code for fitting multivariate t distribution (ECME)
I am looking to fit some data with central multivariate t distributions.
I understand an ECME algorithm is the most promising way to do this. I wondered if anyone knew of any existing code for ...
3
votes
1answer
45 views
+50
Determine an unknown number of real world locations from GPS-based reports
I'm working on some software which should determine real world locations (f.e. speed cams) from several GPS-based reports. An user will be driving when reporting a location, thus the reports a very ...
0
votes
0answers
19 views
Is it possible to Reduce/Correct Bias through EM algorithm?
I am dealing with few overdispersed count models and using mixed Poisson distributions to deal with overdispsered data. I've used MLE technique to estimate the paramters, however ML estimates are ...
1
vote
0answers
34 views
Does the EM algorithm for mixtures still address the missing data issue?
There is a PDF $p(D| \theta)=p(X,Z| \theta)$ with observed values $X$ but also some missing or incomplete values $Z$ (for eg. resulting from censoring).
The expectation-maximization (EM) algorithm is ...
0
votes
1answer
65 views
r: normalmixEM not consistent?
I have the following data: http://s000.tinyupload.com/?file_id=00083355432555420222
I want to fit a mixture density of two normal distributions.
I have the formula:
\begin{align}
f(l)=\pi ...
0
votes
0answers
39 views
Formulas for fitting the parameters of a linear dynamical system
Using the expectation-maximization algorithm one can fit all the parameters of a linear dynamical system. I know the theory behind it, and I know how to derive the updated parameters from the Kalman ...
1
vote
1answer
123 views
A Poisson EM clustering algorithm in R?
I've been looking for a Poisson expectation-maximization clustering implemented in R. Does anyone know if there is one available or can point me in the right direction?
thanks!
and please let me ...
5
votes
2answers
152 views
Using EM algorithm for record linking
I am interested in linking records across 2 datasets by first name, last name, and birth year. Might this be doable with the EM algorithm, and if so, how?
Consider the following record in the 1st as ...
3
votes
1answer
149 views
Relative advantages of multiple imputation and expectation maximization (EM)
I've got a problem where
$$y = a + b $$
I observe y, but neither $a$ nor $b$. I want to estimate
$$b = f(x) + \epsilon$$
I can estimate $a$, using some sort of regression model. This gives me ...
2
votes
0answers
87 views
Non-increasing Log Likelihood with Expectation Maximization
I am struggling with my implementation of the expectation maximization (EM) algorithm for a certain model. The sequence of log likelihood values is not increasing, which is contradicting the theory.
...
3
votes
0answers
36 views
Can we reconstruct the hidden (latent) variables after executing EM?
The question is in the title. I know that EM algorithm could do maximum likelihood estimation for models that have latent variables. I would like to know can we get the (estimated) value of these ...
8
votes
2answers
287 views
What is the difference between EM and Gradient Ascent
I can't understand what is the difference between the algorithms EM (Expectation Maximization) and Gradient Ascent (or descent).
Is there any condition under which they are equivalent?
Thank you.
2
votes
1answer
127 views
The relationship between expectation-maximization and majorization-minimization
I wonder about the relationship between two methods called expectation-maximization (EM) and majorization-minimization. One of them, the EM algorithm can be used for finding the mode of the likelihood ...
2
votes
0answers
57 views
Time dependant weights in hidden Markov models
I'm trying to modify a standard implementation of a continuous HMM with Gaussian Mixtures so that it internally gives more weight to newer observations in a time series.
Essentially, I'm trying to ...
2
votes
0answers
109 views
Computation of Maximization probabilities of the EM algorithm
I have implemented a semi-supervised Naive Bayes that makes use of the EM algorithm to iteratively learn from unlabeled data in a text classification problem, but I am not sure of the processing done ...
1
vote
0answers
78 views
EM for truncated/censored data, how do those CDF's cancel?
I am practicing basic EM problems for qualifying exams.
I am having trouble with truncated/censored data problems. There is something I don't understand about the complete-data likelihood.
Consider ...
2
votes
2answers
151 views
Finding most informative feature subsets given dataset, clustering algorithm and gold standard partition
I have an $n \times m$ matrix of data $\mathbf{D}$ as well as a $k$-partition $P$ of $n$ indices each representing a row in $\mathbf{D}$. Assuming an arbitrary clustering algorithm $A$, I would like ...
5
votes
1answer
147 views
Combination of variational methods and empirical Bayes
Suppose I have a posterior $p(z, \theta | y, \eta)$ with $y$ observed data, $z$ are hidden variables and $\theta$ are parameters, and $\eta$ is a vector of hyperparameters. I construct a mean field ...
1
vote
0answers
57 views
Root Convergence Rate of EM or MM Iteration [closed]
I have an iterative sequence for optimizing an EM/MM algorithm based loss function $L(X)$ with $t$ being the iteration number as:
$X_t=ABX_{t-1}+CX_{t-1}+X_{t-1}$ where $A$ is a diagonal matrix, $B$ ...
1
vote
2answers
143 views
Learning a mapping from one time series to another with a Kalman Filter
I am interested in finding the relation between two (possibly multi dimensional) time series $x_{1:T}$ and $y_{1:T}$. I wonder how I can do that with a linear dynamical system/Kalman filter.
My ...
8
votes
3answers
228 views
Fast alternatives to the EM algorithm
Are there any speedy alternatives to the EM algorithm for learning models with latent variables (especially pLSA)? I'm okay with sacrificing precision in favor of speed.
1
vote
2answers
102 views
How is EM used in the sense of data mining on images?
I understand how EM is used in the sense of estimating the Gaussian model that underlies a set of data, but its unclear how this is applicable.
I am trying to understand how EM might be used to ...
1
vote
0answers
138 views
Simple problem formulation for EM algorithm
I understand the EM algorithm, I understand for example how we get $Q(\theta, \theta^t)$, but I have trouble translating a real-world problem into the EM framework.
For example, I'm given this ...
10
votes
2answers
233 views
Finding number of gaussians in a finite mixture with Wilks' theorem?
Assume I have a set of independent, identically distributed univariate observations $x$ and two hypotheses about how $x$ was generated:
$H_0$: $x$ is drawn from a single Gaussian distribution with ...
