Package jline.opt.variables

Class TaskReplication

java.lang.Object

jline.opt.variables.DecisionVariable

jline.opt.variables.LqnDecisionVariable

jline.opt.variables.TaskReplication

public class TaskReplication
extends LqnDecisionVariable

Optimize the replication (fan-out replicas) of an LQN Task (integer). Mirrors native-Python TaskReplication.

Field Summary

Fields inherited from class jline.opt.variables.DecisionVariable

dimension, name

Constructor Summary

Constructors

Constructor	Description
TaskReplication(String taskName, int minValue, int maxValue)
TaskReplication(String taskName, int minValue, int maxValue, String name)
TaskReplication(Task task, int minValue, int maxValue)

Method Summary

Modifier and Type	Method	Description
void	applyLqn(LayeredNetwork model, Object value)	Apply a decoded value to a (copied) LayeredNetwork model.
Object	currentValue(Object model)	The variable's current (decoded) value in the given model, or null.
Object	decode(double[] x)	Decode the encoded slice (length DecisionVariable.getDimension()) to a value.
double[][]	getBounds()	Bounds per encoded dimension, each {low, high}.
List<String>	getLayer(Object model)	LQN layer name(s) this variable perturbs, or null for flat-network variables.
String	getVariableType()	Type identifier used by decomposition and the gradient dispatcher.

Methods inherited from class jline.opt.variables.LqnDecisionVariable

apply

Methods inherited from class jline.opt.variables.DecisionVariable

connectionMatrix, getDimension, getName, indexOfNode, resolveClass, resolveNode, unitBounds

Methods inherited from class java.lang.Object

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

Constructor Details

TaskReplication

public TaskReplication(Task task,
 int minValue,
 int maxValue)

TaskReplication

public TaskReplication(String taskName,
 int minValue,
 int maxValue)

TaskReplication

public TaskReplication(String taskName,
 int minValue,
 int maxValue,
 String name)

Method Details

getBounds

public double[][] getBounds()

Description copied from class: DecisionVariable

Bounds per encoded dimension, each {low, high}. Standard is {0,1}.

Specified by:

getBounds in class DecisionVariable

decode

public Object decode(double[] x)

Description copied from class: DecisionVariable

Decode the encoded slice (length DecisionVariable.getDimension()) to a value.

Specified by:

decode in class DecisionVariable

applyLqn

public void applyLqn(LayeredNetwork model,
 Object value)

Description copied from class: LqnDecisionVariable

Apply a decoded value to a (copied) LayeredNetwork model.

Specified by:

applyLqn in class LqnDecisionVariable

getVariableType

public String getVariableType()

Description copied from class: DecisionVariable

Type identifier used by decomposition and the gradient dispatcher.

Specified by:

getVariableType in class DecisionVariable

getLayer

public List<String> getLayer(Object model)

Description copied from class: DecisionVariable

LQN layer name(s) this variable perturbs, or null for flat-network variables. Used by layer freezing (both explicit frozen_layers and adaptive auto_freeze): a variable whose layer set intersects the frozen set is held fixed. The model argument is the LayeredNetwork the variable is applied to. LQN variable subclasses override this.

Overrides:

getLayer in class DecisionVariable

currentValue

public Object currentValue(Object model)

Description copied from class: DecisionVariable

The variable's current (decoded) value in the given model, or null. Used by layer freezing to hold a variable at the model's existing parameter value. Flat and non-introspectable variables return null. LQN variable subclasses override this.

Overrides:

currentValue in class DecisionVariable