breeze/breeze.optimize/AdaDeltaGradientDescent

AdaDeltaGradientDescent

class AdaDeltaGradientDescent[T](rho: Double, maxIter: Int, tolerance: Double, improvementTolerance: Double, minImprovementWindow: Int)(implicit vspace: MutableFiniteCoordinateField[T, _, Double], rand: RandBasis) extends StochasticGradientDescent[T]

Created by jda on 3/17/15.

trait Serializable
class Object
trait Matchable
class Any

Type members

Classlikes

case class History(avgSqGradient: T, avgSqDelta: T)

Inherited types

type State = State[T, Info, History]
Inherited from
FirstOrderMinimizer

Value members

Concrete methods

override def determineStepSize(state: State, f: StochasticDiffFunction[T], dir: T): Double

Inherited methods

def infiniteIterations(f: StochasticDiffFunction[T], state: State): Iterator[State]
Inherited from
FirstOrderMinimizer
def iterations(f: StochasticDiffFunction[T], init: T): Iterator[State]
Inherited from
FirstOrderMinimizer
protected def logger: LazyLogger
Inherited from
SerializableLogging
def minimize(f: StochasticDiffFunction[T], init: T): T
Inherited from
FirstOrderMinimizer

Concrete fields

val epsilon: Double

Inherited fields

val defaultStepSize: Double