Package | Description |
---|---|
org.apache.flink.ml.optimization |
Modifier and Type | Class and Description |
---|---|
class |
L1Regularization$
L_1 regularization penalty. |
class |
L2Regularization$
L_2 regularization penalty. |
class |
NoRegularization$
No regularization penalty.
|
Modifier and Type | Method and Description |
---|---|
DataSet<WeightVector> |
GradientDescent.optimizeWithConvergenceCriterion(DataSet<LabeledVector> dataPoints,
DataSet<WeightVector> initialWeightsDS,
int numberOfIterations,
RegularizationPenalty regularizationPenalty,
double regularizationConstant,
double learningRate,
double convergenceThreshold,
LossFunction lossFunction,
LearningRateMethod.LearningRateMethodTrait learningRateMethod) |
DataSet<WeightVector> |
GradientDescent.optimizeWithoutConvergenceCriterion(DataSet<LabeledVector> data,
DataSet<WeightVector> initialWeightsDS,
int numberOfIterations,
RegularizationPenalty regularizationPenalty,
double regularizationConstant,
double learningRate,
LossFunction lossFunction,
LearningRateMethod.LearningRateMethodTrait optimizationMethod) |
Solver |
Solver.setRegularizationPenalty(RegularizationPenalty regularizationPenalty) |
static Solver |
GradientDescent.setRegularizationPenalty(RegularizationPenalty regularizationPenalty) |
static Solver |
IterativeSolver.setRegularizationPenalty(RegularizationPenalty regularizationPenalty) |
Vector |
GradientDescent.takeStep(Vector weightVector,
Vector gradient,
RegularizationPenalty regularizationPenalty,
double regularizationConstant,
double learningRate)
Calculates the new weights based on the gradient
|
Copyright © 2014–2018 The Apache Software Foundation. All rights reserved.