_Note: This library is still in the early phases of development._

`CEM` is an Elixir framework for applying the 
[cross-entropy method](https://en.wikipedia.org/wiki/Cross-entropy_method) to 
continuous and discrete optimization problems.

This library caters specifically to problems where the probability distribution
for generating candidate solutions belongs to the 
[exponential family](https://en.wikipedia.org/wiki/Exponential_family). This is
not a very restrictive limitation, since a wide range of problems can be solved
using either normal or Bernoulli random variables. 

A [separate repo](https://github.com/epfahl/cem_examples) contains livebooks 
that demonstrate usage examples and setups for certain classes of optimization 
problems.