DM_LBFGS

scalation.optimization.quasi_newton.DM_LBFGS
object DM_LBFGS extends PathMonitor

The DM_LBFGS object implementation of the direction momentum Limited memory Broyden–Fletcher–Goldfarb–Shanno (BFGS) for unconstrained optimization (dmL-BFGS) algorithm.

Attributes

Graph
Supertypes
trait PathMonitor
class Object
trait Matchable
class Any
Self type
DM_LBFGS.type

Members list

Value members

Concrete methods

def dmlbfgsMain(n: Int, x: VectorD, functionLogic: EvaluationLogic | OptimizationLogic, params: LBFGSPrms, momentum: Double, instance: Any): LBFGSResults

Performs the dmL-BFGS optimization that optimizes variables to minimize a function value using momentum on the variables and the line search direction.

Performs the dmL-BFGS optimization that optimizes variables to minimize a function value using momentum on the variables and the line search direction.

Attributes

Inherited methods

def add2Path(x: VectorD): Unit

Adds a new multidimensional point to the path being monitored.

Adds a new multidimensional point to the path being monitored.

Value parameters

x

the data point to be added to the path being monitored.

Attributes

Inherited from:
PathMonitor
def clearPath(): Unit

Clears the current path being monitored.

Clears the current path being monitored.

Attributes

Inherited from:
PathMonitor
def getPath: ArrayBuffer[VectorD]

Returns a deep copy of the data path being monitored.

Returns a deep copy of the data path being monitored.

Attributes

Returns

ArrayBuffern [VectorD], a deep copy of the data path being monitored.

Inherited from:
PathMonitor