Error, How to deal with the error of "Matrix must be positive definite"

[ido]

From [email protected] on August 27, 2013 02:54:20

What steps will reproduce the problem? 1.words frequencies in documents of each slice are used as the input of hmmMixGaussTiedTest.m

1. Then it output "initializing model for EM; Error using chol; Matrix must be positive definite."

I think that the Sigma is not positive definite.

How to deal with this situation? What is the expected output? What do you see instead? I want to estimate the parameters of HMM with Gaussian Mixture Model. What version / revision of the product are you using? On what operating system? pmtk3 Please provide any additional information below. details are as bellow:

initializing model for EM Error using chol Matrix must be positive definite.

Error in gaussLogprob (line 52) R = chol(Sigma);

Error in mixGaussInferLatent (line 17) logPz(:, k) = logMix(k) + gaussLogprob(mu(:, k), Sigma(:, :, k), X);

Error in mixGaussFit>estep (line 52) [weights, ll] = mixGaussInferLatent(model, data);

Error in emAlgo (line 62) [ess, ll] = estep(model, data);

Error in mixGaussFit (line 25)

[model, loglikHist] = emAlgo(model, data, initFn, @estep, @mstep , ...

Original issue: http://code.google.com/p/pmtk3/issues/detail?id=60