OWLQN

class OWLQN[K, T](convergenceCheck: ConvergenceCheck[T], m: Int, l1reg: K => Double)(implicit space: MutableEnumeratedCoordinateField[T, K, Double]) extends LBFGS[T] with SerializableLogging

Implements the Orthant-wise Limited Memory QuasiNewton method, which is a variant of LBFGS that handles L1 regularization.

Paper is Andrew and Gao (2007) Scalable Training of L1-Regularized Log-Linear Models

class LBFGS[T]
trait Serializable
trait Minimizer[T, DiffFunction[T]]
class Object
trait Matchable
class Any

Type members

Inherited types

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

Value members

Constructors

def this(maxIter: Int, m: Int, l1reg: K => Double, tolerance: Double)(implicit space: MutableEnumeratedCoordinateField[T, K, Double])
def this(maxIter: Int, m: Int, l1reg: K => Double)(implicit space: MutableEnumeratedCoordinateField[T, K, Double])
def this(maxIter: Int, m: Int, l1reg: Double, tolerance: Double)(implicit space: MutableEnumeratedCoordinateField[T, K, Double])
def this(maxIter: Int, m: Int, l1reg: Double)(implicit space: MutableEnumeratedCoordinateField[T, K, Double])
def this(maxIter: Int, m: Int)(implicit space: MutableEnumeratedCoordinateField[T, K, Double])

Inherited methods

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