edu.stanford.nlp.maxent.iis
Class CGRunner

java.lang.Object
  |
  +--edu.stanford.nlp.maxent.iis.CGRunner

public class CGRunner

extends Object

This class will call Conjugate Gradient on a LambdaSolve object to find optimal parameters, including imposing a Gaussian prior on those parameters.

Constructor Summary

CGRunner(LambdaSolve prob, String filename)
Set up a LambdaSolve problem for solution by Conjugate Gradient.

CGRunner(LambdaSolve prob, String filename, double tol, boolean useGaussianPrior, double priorSigmaS)
Set up a LambdaSolve problem for solution by Conjugate Gradient.

Method Summary

void	solve() Solves the problem using CG.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

CGRunner

public CGRunner(LambdaSolve prob,
                String filename)

Set up a LambdaSolve problem for solution by Conjugate Gradient. Uses a Gaussian prior with a sigma² of 0.5.

Parameters:

prob - The problem to solve

filename - Used (with extension) to save intermediate results.

CGRunner

public CGRunner(LambdaSolve prob,
                String filename,
                double tol,
                boolean useGaussianPrior,
                double priorSigmaS)

Set up a LambdaSolve problem for solution by Conjugate Gradient.

Parameters:

prob - The problem to solve

filename - Used (with extension) to save intermediate results.

tol - Tolerance of errors (passed to CG)

useGaussianPrior - True if parameters should be penalized with a gaussian prior for smoothing

priorSigmaS - The prior sigma²: this doubled will be used to divide the lambda² values as the prior penalty

Method Detail

solve

public void solve()

Solves the problem using CG. The solution is stored in the lambda array of prob.