SimpleSGD

class SimpleSGD[T](initialStepSize: Double, maxIter: Int)(implicit vs: NormedModule[T, Double]) extends StochasticGradientDescent[T]
trait Serializable
class Object
trait Matchable
class Any

Type members

Types

type History = Unit

Inherited types

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

Value members

Concrete methods

def updateHistory(newX: T, newGrad: T, newValue: Double, f: StochasticDiffFunction[T], oldState: State): History

Inherited methods

Choose a step size scale for this iteration.

Choose a step size scale for this iteration.

Default is eta / math.pow(state.iter + 1,2.0 / 3.0)

Inherited from:
StochasticGradientDescent
protected def logger: LazyLogger
Inherited from:
SerializableLogging
def minimize(f: StochasticDiffFunction[T], init: T): T
Inherited from:
FirstOrderMinimizer