Package org.apache.spark.mllib.optimization

Class L1Updater

Object

org.apache.spark.mllib.optimization.Updater

org.apache.spark.mllib.optimization.L1Updater

All Implemented Interfaces:

Serializable, scala.Serializable

public class L1Updater
extends Updater

Updater for L1 regularized problems. R(w) = ||w||_1 Uses a step-size decreasing with the square root of the number of iterations.

Instead of subgradient of the regularizer, the proximal operator for the L1 regularization is applied after the gradient step. This is known to result in better sparsity of the intermediate solution.

The corresponding proximal operator for the L1 norm is the soft-thresholding function. That is, each weight component is shrunk towards 0 by shrinkageVal.

If w is greater than shrinkageVal, set weight component to w-shrinkageVal. If w is less than -shrinkageVal, set weight component to w+shrinkageVal. If w is (-shrinkageVal, shrinkageVal), set weight component to 0.

Equivalently, set weight component to signum(w) * max(0.0, abs(w) - shrinkageVal)

See Also:

• Serialized Form

Constructor Summary

Constructors

Constructor	Description
L1Updater()

Method Summary

Modifier and Type	Method	Description
scala.Tuple2<Vector,Object>	compute(Vector weightsOld, Vector gradient, double stepSize, int iter, double regParam)	Compute an updated value for weights given the gradient, stepSize, iteration number and regularization parameter.

Methods inherited from class java.lang.Object

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

Constructor Details

L1Updater

public L1Updater()

Method Details

compute

public scala.Tuple2<Vector,Object> compute(Vector weightsOld,
 Vector gradient,
 double stepSize,
 int iter,
 double regParam)

Description copied from class: Updater

Compute an updated value for weights given the gradient, stepSize, iteration number and regularization parameter. Also returns the regularization value regParam * R(w) computed using the *updated* weights.

Specified by:

compute in class Updater

Parameters:

weightsOld - - Column matrix of size dx1 where d is the number of features.

gradient - - Column matrix of size dx1 where d is the number of features.

stepSize - - step size across iterations

iter - - Iteration number

regParam - - Regularization parameter

Returns:

A tuple of 2 elements. The first element is a column matrix containing updated weights, and the second element is the regularization value computed using updated weights.