public abstract class LSMSolver extends Iced
Modifier and Type | Class and Description |
---|---|
static class |
LSMSolver.ADMMSolver |
static class |
LSMSolver.GeneralizedGradientSolver
Generalized gradient solver for solving LSM problem with combination of L1 and L2 penalty.
|
static class |
LSMSolver.LSMSolverException |
static class |
LSMSolver.LSMSolverType |
Modifier and Type | Field and Description |
---|---|
double |
_alpha |
protected boolean |
_converged |
java.lang.String |
_id |
Key |
_jobKey |
double |
_lambda |
Constructor and Description |
---|
LSMSolver(double lambda,
double alpha) |
Modifier and Type | Method and Description |
---|---|
boolean |
converged() |
abstract java.lang.String |
name() |
protected static double |
shrinkage(double x,
double kappa) |
abstract boolean |
solve(Gram gram,
double[] xy,
double yy,
double[] newBeta) |
abstract com.google.gson.JsonObject |
toJson() |
clone, frozenType, init, newInstance, read, toDocField, write, writeJSON, writeJSONFields
public double _lambda
public final double _alpha
public Key _jobKey
public java.lang.String _id
protected boolean _converged
public abstract boolean solve(Gram gram, double[] xy, double yy, double[] newBeta)
xx
- - gram matrix. gaussian: X'X, binomial:(1/4)X'Xxy
- - guassian: -X'y binomial: -(1/4)X'(XB + (y-p)/(p*1-p))yy
- - beta
- - previous vector of coefficients, will be modified/destroyednewBeta
- - resulting vector of coefficientspublic abstract com.google.gson.JsonObject toJson()
public final boolean converged()
public abstract java.lang.String name()
protected static double shrinkage(double x, double kappa)