Sufficient statistic and unbiased estimation
Sufficient statistics are at the heart of the quest for good unbiased estimators (low variance) of the parameter θ, ...
For each parameter distribution, the associated counts correspond to sufficient statistics.
EM is particularly useful when the likelihood is an exponential family: the E-step becomes the sum of expectations of sufficient statistics, and the M-step involves maximizing a linear function.
" VFML provides code to help read and process training data, to gather sufficient statistics from it, ADTs for several important machine learning structures, and various helper code.
 See also: Distribution, Demon, Variance, Estimation, Density
  
|
RSS
