markovmodel / msmtools

90%

devel: %

LAST BUILD ON BRANCH rev_mle_convergence_tweaks

branch: rev_mle_convergence_tweaks

CHANGE BRANCH

x

Reset

• rev_mle_convergence_tweaks
• add_sparse_options
• confconst
• count_matrix_performance
• devel
• dtraj_api
• fix_trev_norm
• minor_corrections
• minor_improvements
• pcca_fixes
• relax_pcca_assertions
• remove_old_cmatrix_code
• statdist_more_robust
• statdist_weakly_connected
• v1.0.1
• v1.0.2
• v1.0.3
• v1.0.4
• v1.1
• v1.1.1
• v1.1.2
• v1.1.3

Build # 115

Build Type

push

travis-ci

Committed by franknoe

Commit Message

[estimation: reversible tmatrix MLE and sampler]: Added option to suppress the not-converged warning. Using that option and running only 100 steps in the initialization of the reversible transition matrix sampler. That's sufficient for the sampler because the MLE is just a starting point anyway. In cases where the reversible MLE doesn't converge well - and that seems to happen often for the fractional counts employed in Bayesian methods - we would otherwise optimize for 1M steps, just to throw that result away in the first sampling step. This change makes a huge performance difference for the Bayesian HMM, where a transition matrix sampling is run for every iteration of the algorithm (usually 100 times or more).

Run Details

8363 of 9333 relevant lines covered (89.61%)

1.79 hits per line