com.cra.figaro.algorithm.lazyfactored
LazyVariableElimination
Called when the algorithm is killed.
Called when the algorithm is killed. By default, does nothing. Can be overridden.
Some variable elimination algorithms, such as computing the most probable explanation, record values of variables as they are eliminated.
Some variable elimination algorithms, such as computing the most probable explanation, record values of variables as they are eliminated. Such values are stored in a factor that maps values of the other variables to a value of the eliminated variable. This factor is produced by finding the value of the variable that "maximizes" the entry associated with the value in the product factor resulting from eliminating this variable, for some maximization function. The recordingFunction determines which of two entries is greater according to the maximization function. It returns true iff the second entry is greater. The recording function is an option so that variable elimination algorithms that do not use it can ignore it.
The algorithm to compute probability of specified evidence in a dependent universe.
The algorithm to compute probability of specified evidence in a dependent universe. We use () => Double to represent this algorithm instead of an instance of ProbEvidenceAlgorithm. Typical usage is to return the result of ProbEvidenceAlgorithm.computeProbEvidence when invoked.
A list of universes that depend on this universe such that evidence on those universes should be taken into account in this universe.
A list of universes that depend on this universe such that evidence on those universes should be taken into account in this universe.
The current depth to which the algorithm should be run.
The current depth to which the algorithm should be run.
Kill the algorithm.
Kill the algorithm.
Resume the algorithm by increasing the depth and running again.
Resume the algorithm by increasing the depth and running again.
Start the algorithm.
Start the algorithm. This will run the algorithm to one depth.
Stop the algorithm.
Stop the algorithm.
Method for choosing the elimination order.
Method for choosing the elimination order. The default order chooses first the variable that minimizes the number of extra factor entries that would be created when it is eliminated. Override this method if you want a different rule.
Postprocess the factors produced by eliminating variables, assuming the entire model has been expanded so the lower and upper bounds are the same.
Postprocess the factors produced by eliminating variables, when the lower and upper bounds may be different.
Postprocess the factors produced by eliminating variables, when the lower and upper bounds may be different.
the factors produced with the upperBounds flag = false
the factors produced with the upperBounds flag = true
Create the necessary factors.
Create the necessary factors.
elements that have been expanded that need factors created
query targets
flag indicating whether lower (false) or upper (true) bounds should be computed for unexpanded parts of the model
Get the elements that are needed by the query target variables and the evidence variables.
Get the elements that are needed by the query target variables and the evidence variables. Also compute the values of those variables to the given depth. Only get factors for elements that are actually used by the target variables. This is more efficient. Also, it avoids problems when values of unused elements have not been computed.
In addition to getting all the needed elements, it determines if any of the conditioned, constrained, or dependent universe parent elements has * in its range. If any of these elements has * in its range, the lower and upper bounds of factors will be different, so we need to compute both. If they don't, we don't need to compute bounds.
Called when the algorithm is started before running any steps.
Called when the algorithm is started before running any steps. By default, does nothing. Can be overridden.
Kill the algorithm so that it is inactive.
Kill the algorithm so that it is inactive. It will no longer be able to provide answers.Throws AlgorithmInactiveException if the algorithm is not active.
Returns the lower and upper bounds of the probability of the target.
Increase the depth and run the algorithm again.
Increase the depth and run the algorithm again.
Resume the computation of the algorithm, if it has been stopped.
Resume the computation of the algorithm, if it has been stopped. Throws AlgorithmInactiveException if the algorithm is not active.
Run the algorithm to the given depth.
Run the algorithm to the given depth.
The sum, product operations on the factor types and appropriate values for zero and one must be defined.
The sum, product operations on the factor types and appropriate values for zero and one must be defined.
Start the algorithm and make it active.
Start the algorithm and make it active. After it returns, the algorithm must be ready to provide answers. Throws AlgorithmActiveException if the algorithm is already active.
Stop the algorithm from computing.
Stop the algorithm from computing. The algorithm is still ready to provide answers after it returns. Throws AlgorithmInactiveException if the algorithm is not active.
The universe on which this variable elimination algorithm should be applied.
The universe on which this variable elimination algorithm should be applied.
Algorithm that lazily performs variable elimination. This algorithm is a lazy algorithm that can be run to any depth. Given a depth, it expands the model up to that depth and creates factors for the expanded elements. It also creates factors that capture the effect of parts of the model that have not been expanded on the query targets. These factors are used to compute lower or upper bounds on the queries. Then it uses ordinary variable elimination to solve these factors.