hex.glm

Class GLMTask

java.lang.Object

hex.glm.GLMTask

public abstract class GLMTask
extends java.lang.Object

All GLM related distributed tasks: YMUTask - computes response means on actual datasets (if some rows are ignored - e.g ignoring rows with NA and/or doing cross-validation) GLMGradientTask - computes gradient at given Beta, used by L-BFGS, for KKT condition check GLMLineSearchTask - computes residual deviance(s) at given beta(s), used by line search (both L-BFGS and IRLSM) GLMIterationTask - used by IRLSM to compute Gram matrix and response t(X) W X, t(X)Wz

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	GLMTask.GLMCoordinateDescentTask
static class	GLMTask.GLMIterationTask One iteration of glm, computes weighted gram matrix and t(x)*y vector and t(y)*y scalar.
static class	GLMTask.LBFGS_LogisticGradientTask Tassk with simplified gradient computation for logistic regression (and least squares) Looks like

Constructor Summary

Constructors

Constructor and Description
GLMTask()

Method Summary

Methods inherited from class java.lang.Object

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

Constructor Detail

GLMTask

public GLMTask()