Class

com.intel.analytics.bigdl.optim.SGD

Exponential

Related Doc: package SGD

Permalink

case class Exponential(decayStep: Int, decayRate: Double, stairCase: Boolean = false) extends LearningRateSchedule with Product with Serializable

Exponential is a learning rate schedule, which rescale the learning rate by lr_{n + 1} = lr * decayRate ^ (iter / decayStep)

decayStep

the inteval for lr decay

decayRate

decay rate

stairCase

if true, iter / decayStep is an integer division and the decayed learning rate follows a staircase function.

Linear Supertypes
Serializable, Serializable, Product, Equals, LearningRateSchedule, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. Exponential
  2. Serializable
  3. Serializable
  4. Product
  5. Equals
  6. LearningRateSchedule
  7. AnyRef
  8. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new Exponential(decayStep: Int, decayRate: Double, stairCase: Boolean = false)

    Permalink

    decayStep

    the inteval for lr decay

    decayRate

    decay rate

    stairCase

    if true, iter / decayStep is an integer division and the decayed learning rate follows a staircase function.

Value Members

  1. final def !=(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  2. final def ##(): Int

    Permalink
    Definition Classes
    AnyRef → Any

  3. final def ==(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any

  4. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any

  5. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  6. var currentRate: Double

    Permalink
    Definition Classes
    LearningRateSchedule

  7. val decayRate: Double

    Permalink

    decay rate

  8. val decayStep: Int

    Permalink

    the inteval for lr decay

  9. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  10. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )

  11. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any

  12. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any

  13. final def ne(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef

  14. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef

  15. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef

  16. val stairCase: Boolean

    Permalink

    if true, iter / decayStep is an integer division and the decayed learning rate follows a staircase function.

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

    Permalink
    Definition Classes
    AnyRef

  18. def updateHyperParameter[T](optimMethod: SGD[T]): Unit

    Permalink

    update learning rate by config table and state table

    update learning rate by config table and state table

    optimMethod

    init optiMethod.

    Definition Classes
    Exponential → LearningRateSchedule

  19. final def wait(): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

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

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

  21. final def wait(arg0: Long): Unit

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Deprecated Value Members

  1. def updateHyperParameter(config: Table, state: Table): Unit

    Permalink
    Definition Classes
    LearningRateSchedule
    Annotations
    @deprecated
    Deprecated

    (Since version 0.2.0) Please input SGD instead of Table

Inherited from Serializable

Inherited from Serializable

Inherited from Product

Inherited from Equals

Inherited from LearningRateSchedule

Inherited from AnyRef

Inherited from Any

Ungrouped