Generic CE Algorithm
- Choose initial parameter vector ; set t = 1.
- Generate a random sample from
- Solve for, where
- If convergence is reached then stop; otherwise, increase t by 1 and reiterate from step 2.
In several cases, the solution to step 3 can be found analytically. Situations in which this occurs are
- When belongs to the natural exponential family
- When is discrete with finite support
- When and, then corresponds to the maximum likelihood estimator based on those .
Read more about this topic: Cross-entropy Method
Famous quotes containing the word generic:
““Mother” has always been a generic term synonymous with love, devotion, and sacrifice. There’s always been something mystical and reverent about them. They’re the Walter Cronkites of the human race . . . infallible, virtuous, without flaws and conceived without original sin, with no room for ambivalence.”
—Erma Bombeck (20th century)