hex.glm

Class GLM.GLMGradientSolver

java.lang.Object

hex.optimization.L_BFGS.GradientSolver

hex.glm.GLM.GLMGradientSolver

Enclosing class:

GLM

public static final class GLM.GLMGradientSolver
extends L_BFGS.GradientSolver

Gradient and line search computation for L_BFGS and also L_BFGS solver wrapper (for ADMM)

Constructor Summary

Constructors

Constructor and Description
GLM.GLMGradientSolver(GLMModel.GLMParameters glmp, DataInfo dinfo, double lambda, double ymu, double wsum)
GLM.GLMGradientSolver(GLMModel.GLMParameters glmp, DataInfo dinfo, double lambda, double ymu, double wsum, water.fvec.Vec rowFilter)

Method Summary

Methods

Modifier and Type	Method and Description
GLM.GLMGradientInfo	getGradient(double[] beta) Evaluate gradient at solution beta.
double[]	getObjVals(double[] beta, double[] direction, int nSteps, double initialStep, double stepDec) Evaluate objective values at k line search points beta_k.
GLM.GLMGradientSolver	setBetaStart(double[] beta)

Methods inherited from class hex.optimization.L_BFGS.GradientSolver

doLineSearch

Methods inherited from class java.lang.Object

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

Constructor Detail

GLM.GLMGradientSolver

public GLM.GLMGradientSolver(GLMModel.GLMParameters glmp,
                     DataInfo dinfo,
                     double lambda,
                     double ymu,
                     double wsum)

GLM.GLMGradientSolver

public GLM.GLMGradientSolver(GLMModel.GLMParameters glmp,
                     DataInfo dinfo,
                     double lambda,
                     double ymu,
                     double wsum,
                     water.fvec.Vec rowFilter)

Method Detail

setBetaStart

public GLM.GLMGradientSolver setBetaStart(double[] beta)

getGradient

public GLM.GLMGradientInfo getGradient(double[] beta)

Description copied from class: L_BFGS.GradientSolver

Evaluate gradient at solution beta.

Specified by:

getGradient in class L_BFGS.GradientSolver

Returns:

getObjVals

public double[] getObjVals(double[] beta,
                  double[] direction,
                  int nSteps,
                  double initialStep,
                  double stepDec)

Description copied from class: L_BFGS.GradientSolver

Evaluate objective values at k line search points beta_k. When used as part of default line search behavior, the line search points are expected to be beta_k = beta + direction * _startStep * _stepDec^k

Specified by:

getObjVals in class L_BFGS.GradientSolver

Parameters:

beta - - initial vector of coefficients

direction - - search direction

Returns:

objective values evaluated at k line-search points beta + pk*step[k]