OptimizableObjectives

Type Members

class AbsoluteUnivariate extends UnivariateOptimizableObjective[Double]
type Binary = UnivariateOptimizableObjective[Int]

General type for objective functions for binary classification
class EpsilonInsensitiveAbsMultivariate extends MultivariateOptimizableObjective[la.Tensor1]
class EpsilonInsensitiveAbsUnivariate extends UnivariateOptimizableObjective[Double]
class EpsilonInsensitiveSqMultivariate extends MultivariateOptimizableObjective[la.Tensor1]
class EpsilonInsensitiveSqUnivariate extends UnivariateOptimizableObjective[Double]
class HingeBinary extends UnivariateOptimizableObjective[Int]
class HingeMulticlass extends MultivariateOptimizableObjective[Int]
class HingeScaledBinary extends UnivariateOptimizableObjective[Int]
class HingeSqMulticlass extends MultivariateOptimizableObjective[Int]
class LogBinary extends UnivariateOptimizableObjective[Int]
class LogMulticlass extends MultivariateOptimizableObjective[Int]
type Multiclass = MultivariateOptimizableObjective[Int]

General type for multivariate linear objective functions for clasification
class SmoothHingeBinary extends UnivariateOptimizableObjective[Int]
class SparseLogMulticlass extends MultivariateOptimizableObjective[Int]
class SquaredMultivariate extends MultivariateOptimizableObjective[la.Tensor1]
class SquaredUnivariate extends UnivariateOptimizableObjective[Double]
type UnivariateLinkFunction = (Double) ⇒ Double

Value Members

final def !=(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def !=(arg0: Any): Boolean

Definition Classes
Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def ==(arg0: Any): Boolean

Definition Classes
Any
val absoluteUnivariate: AbsoluteUnivariate

Absolute objective for univariate regression
final def asInstanceOf[T0]: T0

Definition Classes
Any
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def epsilonInsensitiveAbsMultivariate(epsilon: Double): EpsilonInsensitiveAbsMultivariate

Epsilon-insensitive absolute objective for multivariate regression
Epsilon-insensitive absolute objective for multivariate regression
epsilon
The tolerance of the objective function
returns
An objective function
def epsilonInsensitiveAbsUnivariate(epsilon: Double): EpsilonInsensitiveAbsUnivariate

Epsilon-insensitive absolute objective for univariate regression
Epsilon-insensitive absolute objective for univariate regression
epsilon
The tolerance of the objective function
returns
An objective function
def epsilonInsensitiveSqMultivariate(epsilon: Double): EpsilonInsensitiveSqMultivariate

Epsilon-insensitive squared objective for multivariate regression
Epsilon-insensitive squared objective for multivariate regression
epsilon
The tolerance of the objective function
returns
An objective function
def epsilonInsensitiveSqUnivariate(epsilon: Double): EpsilonInsensitiveSqUnivariate

Epsilon-insensitive squared objective for univariate regression
Epsilon-insensitive squared objective for univariate regression
epsilon
The tolerance of the objective function
returns
An objective function
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def hashCode(): Int

Definition Classes
AnyRef → Any
val hingeBinary: HingeBinary

Hinge objective for binary classification
val hingeMulticlass: HingeMulticlass

Hinge objective for multiclass classification
def hingeScaledBinary(posCost: Double = 1.0, negCost: Double = 1.0): HingeScaledBinary

A variant of the hinge objective for binary classification which can have different costs for type 1 and type 2 errors.
A variant of the hinge objective for binary classification which can have different costs for type 1 and type 2 errors.
posCost
The cost of predicting positive when the label is negative
negCost
The cost of predicting negative when the label is positive
returns
An objective function
val hingeSqMulticlass: HingeSqMulticlass

Squared hinge objective for multiclass classification
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
val logBinary: LogBinary

Log objective for binary classification
val logMulticlass: LogMulticlass

Log objective for multiclass classification.
Log objective for multiclass classification. Inefficient.
val logisticLinkFunction: (Double) ⇒ Double

The logistic sigmoid function.
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def smoothHingeBinary(gamma: Double = 1.0, margin: Double = 1.0, posCost: Double = 1.0, negCost: Double = 1.0): SmoothHingeBinary

A smoothed (Lipschitz gradient) variant of the hinge objective for binary classification which can have different costs for type 1 and type 2 errors and adjustable margin.
A smoothed (Lipschitz gradient) variant of the hinge objective for binary classification which can have different costs for type 1 and type 2 errors and adjustable margin.
gamma
Adjusts how smoothly the hinge drops down to zero. Higher is more smooth, zero gives unsmoothed hinge.
margin
The number that you need to predict above to achieve the maximum objective score.
posCost
The cost of predicting positive when the label is negative.
negCost
The cost of predicting negative when the label is positive.
returns
An objective function
val sparseLogMulticlass: SparseLogMulticlass

Sparse Log objective for multiclass classification; very efficient.
val squaredLossLinkFunction: (Double) ⇒ Double
val squaredMultivariate: SquaredMultivariate

Squared objective for multivariate regression
val squaredUnivariate: SquaredUnivariate

Squared objective for univariate regression
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
AnyRef → Any
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )

object OptimizableObjectives

Type Members

class AbsoluteUnivariate extends UnivariateOptimizableObjective[Double]

type Binary = UnivariateOptimizableObjective[Int]

class EpsilonInsensitiveAbsMultivariate extends MultivariateOptimizableObjective[la.Tensor1]

class EpsilonInsensitiveAbsUnivariate extends UnivariateOptimizableObjective[Double]

class EpsilonInsensitiveSqMultivariate extends MultivariateOptimizableObjective[la.Tensor1]

class EpsilonInsensitiveSqUnivariate extends UnivariateOptimizableObjective[Double]

class HingeBinary extends UnivariateOptimizableObjective[Int]

class HingeMulticlass extends MultivariateOptimizableObjective[Int]

class HingeScaledBinary extends UnivariateOptimizableObjective[Int]

class HingeSqMulticlass extends MultivariateOptimizableObjective[Int]

class LogBinary extends UnivariateOptimizableObjective[Int]

class LogMulticlass extends MultivariateOptimizableObjective[Int]

type Multiclass = MultivariateOptimizableObjective[Int]

class SmoothHingeBinary extends UnivariateOptimizableObjective[Int]

class SparseLogMulticlass extends MultivariateOptimizableObjective[Int]

class SquaredMultivariate extends MultivariateOptimizableObjective[la.Tensor1]

class SquaredUnivariate extends UnivariateOptimizableObjective[Double]

type UnivariateLinkFunction = (Double) ⇒ Double

Value Members

final def !=(arg0: AnyRef): Boolean

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: AnyRef): Boolean

final def ==(arg0: Any): Boolean

val absoluteUnivariate: AbsoluteUnivariate

final def asInstanceOf[T0]: T0

def clone(): AnyRef

def epsilonInsensitiveAbsMultivariate(epsilon: Double): EpsilonInsensitiveAbsMultivariate

def epsilonInsensitiveAbsUnivariate(epsilon: Double): EpsilonInsensitiveAbsUnivariate

def epsilonInsensitiveSqMultivariate(epsilon: Double): EpsilonInsensitiveSqMultivariate

def epsilonInsensitiveSqUnivariate(epsilon: Double): EpsilonInsensitiveSqUnivariate

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

final def getClass(): Class[_]

def hashCode(): Int

val hingeBinary: HingeBinary

val hingeMulticlass: HingeMulticlass

def hingeScaledBinary(posCost: Double = 1.0, negCost: Double = 1.0): HingeScaledBinary

val hingeSqMulticlass: HingeSqMulticlass

final def isInstanceOf[T0]: Boolean

val logBinary: LogBinary

val logMulticlass: LogMulticlass

val logisticLinkFunction: (Double) ⇒ Double

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def smoothHingeBinary(gamma: Double = 1.0, margin: Double = 1.0, posCost: Double = 1.0, negCost: Double = 1.0): SmoothHingeBinary

val sparseLogMulticlass: SparseLogMulticlass

val squaredLossLinkFunction: (Double) ⇒ Double

val squaredMultivariate: SquaredMultivariate

val squaredUnivariate: SquaredUnivariate

final def synchronized[T0](arg0: ⇒ T0): T0

def toString(): String

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

Inherited from AnyRef

Inherited from Any

Ungrouped