opennlp.tools.ml.maxent.quasinewton

Class QNMinimizer

java.lang.Object

opennlp.tools.ml.maxent.quasinewton.QNMinimizer

public class QNMinimizer
extends Object

Implementation of L-BFGS which supports L1-, L2-regularization and Elastic Net for solving convex optimization problems.

Usage example:

  // Quadratic function f(x) = (x-1)^2 + 10
  // f obtains its minimum value 10 at x = 1
  Function f = new Function() {

    @Override
    public int getDimension() {
      return 1;
    }

    @Override
    public double valueAt(double[] x) {
      return Math.pow(x[0]-1, 2) + 10;
    }

    @Override
    public double[] gradientAt(double[] x) {
      return new double[] { 2*(x[0]-1) };
    }

  };

  QNMinimizer minimizer = new QNMinimizer();
  double[] x = minimizer.minimize(f);
  double min = f.valueAt(x);
 

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static interface	QNMinimizer.Evaluator Evaluate quality of training parameters.
static class	QNMinimizer.L2RegFunction L2-regularized objective function

Field Summary

Fields

Modifier and Type	Field and Description
static double	CONVERGE_TOLERANCE
static double	INITIAL_STEP_SIZE
static double	L1COST_DEFAULT
static double	L2COST_DEFAULT
static int	M_DEFAULT
static int	MAX_FCT_EVAL_DEFAULT
static double	MIN_STEP_SIZE
static int	NUM_ITERATIONS_DEFAULT
static double	REL_GRAD_NORM_TOL

Constructor Summary

Constructors

Constructor and Description
QNMinimizer()
QNMinimizer(double l1Cost, double l2Cost)
QNMinimizer(double l1Cost, double l2Cost, int iterations)
QNMinimizer(double l1Cost, double l2Cost, int iterations, int m, int maxFctEval)
QNMinimizer(double l1Cost, double l2Cost, int iterations, int m, int maxFctEval, boolean verbose) Constructor

Method Summary

Methods

Modifier and Type	Method and Description
QNMinimizer.Evaluator	getEvaluator()
double[]	minimize(Function function) Find the parameters that minimize the objective function
void	setEvaluator(QNMinimizer.Evaluator evaluator)

Methods inherited from class java.lang.Object

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

Field Detail

CONVERGE_TOLERANCE

public static final double CONVERGE_TOLERANCE

See Also:

Constant Field Values

REL_GRAD_NORM_TOL

public static final double REL_GRAD_NORM_TOL

See Also:

Constant Field Values

INITIAL_STEP_SIZE

public static final double INITIAL_STEP_SIZE

See Also:

Constant Field Values

MIN_STEP_SIZE

public static final double MIN_STEP_SIZE

See Also:

Constant Field Values

L1COST_DEFAULT

public static final double L1COST_DEFAULT

See Also:

Constant Field Values

L2COST_DEFAULT

public static final double L2COST_DEFAULT

See Also:

Constant Field Values

NUM_ITERATIONS_DEFAULT

public static final int NUM_ITERATIONS_DEFAULT

See Also:

Constant Field Values

M_DEFAULT

public static final int M_DEFAULT

See Also:

Constant Field Values

MAX_FCT_EVAL_DEFAULT

public static final int MAX_FCT_EVAL_DEFAULT

See Also:

Constant Field Values

Constructor Detail

QNMinimizer

public QNMinimizer()

QNMinimizer

public QNMinimizer(double l1Cost,
           double l2Cost)

QNMinimizer

public QNMinimizer(double l1Cost,
           double l2Cost,
           int iterations)

QNMinimizer

public QNMinimizer(double l1Cost,
           double l2Cost,
           int iterations,
           int m,
           int maxFctEval)

QNMinimizer

public QNMinimizer(double l1Cost,
           double l2Cost,
           int iterations,
           int m,
           int maxFctEval,
           boolean verbose)

Constructor

Parameters:

l1Cost - L1-regularization cost

l2Cost - L2-regularization cost

iterations - maximum number of iterations

m - number of Hessian updates to store

maxFctEval - maximum number of function evaluations

verbose - verbose output

Method Detail

getEvaluator

public QNMinimizer.Evaluator getEvaluator()

setEvaluator

public void setEvaluator(QNMinimizer.Evaluator evaluator)

minimize

public double[] minimize(Function function)

Find the parameters that minimize the objective function

Parameters:

function - objective function

Returns:

minimizing parameters