Package org.drip.learning.svm
Class DecisionFunctionOperatorBounds
java.lang.Object
org.drip.learning.svm.DecisionFunctionOperatorBounds
public class DecisionFunctionOperatorBounds
extends java.lang.Object
DecisionFunctionOperatorBounds implements the Dot Product Entropy Number Upper Bounds for the
Product of Kernel Feature Map Function and the Scaling Diagonal Operator.
The References are:
The References are:
- Ash, R. (1965): Information Theory Inter-science New York
- Carl, B., and I. Stephani (1990): Entropy, Compactness, and Approximation of Operators Cambridge University Press Cambridge UK
- Gordon, Y., H. Konig, and C. Schutt (1987): Geometric and Probabilistic Estimates of Entropy and Approximation Numbers of Operators Journal of Approximation Theory 49 219-237
- Konig, H. (1986): Eigenvalue Distribution of Compact Operators Birkhauser Basel, Switzerland
- Smola, A. J., A. Elisseff, B. Scholkopf, and R. C. Williamson (2000): Entropy Numbers for Convex Combinations and mlps, in: Advances in Large Margin Classifiers, A. Smola, P. Bartlett, B. Scholkopf, and D. Schuurmans - editors MIT Press Cambridge, MA
- Module = Computational Core Module
- Library = Statistical Learning
- Project = Agnostic Learning Bounds under Empirical Loss Minimization Schemes
- Package = Kernel SVM Decision Function Operator
- Author:
- Lakshmi Krishnamurthy
-
Constructor Summary
Constructors Constructor Description DecisionFunctionOperatorBounds(DiagonalScalingOperator dsoFactorizer, double dblInverseMarginNormBound, double dblFeatureSpaceMaureyConstant, int iFeatureSpaceDimension)
DecisionFunctionOperatorBounds Constructor -
Method Summary
Modifier and Type Method Description DiagonalScalingOperator
factorizingOperator()
Retrieve the Factorizing Diagonal Scaling Operator Instancedouble
featureMaureyOperatorEntropy(int iFeatureSpaceEntropyNumber)
Compute the Decision Function Entropy Number Upper Bound using the Product of the Feature Space's Maurey Upper Bound for the Entropy for the specified Entropy Number and the Scaling Operator Entropy Number Upper Bounddouble
featureMaureyOperatorNorm(int iFeatureSpaceEntropyNumber)
Compute the Decision Function Entropy Number Upper Bound using the Product of the Feature Space's Maurey Upper Bound for the Entropy for the specified Entropy Number and the Scaling Operator Normdouble
featureNormOperatorEntropy()
Compute the Decision Function Entropy Number Upper Bound using the Product of the Feature Space's Norm for the Upper Bound of the Entropy Number and the Scaling Operator Entropy Number Upper Bounddouble
featureSpaceDimension()
Retrieve the Feature Space Dimensiondouble
featureSpaceMaureyBound(int iFeatureSpaceEntropyNumber)
Compute the Feature Space's Maurey Bound for the Entropy Number given the specified Entropy Numberdouble
featureSpaceMaureyConstant()
Retrieve the Feature Space Maurey Constantdouble
infimumUpperBound(int iFeatureSpaceEntropyNumber)
Compute the Infimum of the Decision Function Operator Upper Bound across all the Product Bounds for the specified Feature Space Entropy Numberdouble
inverseMarginNormBound()
Retrieve the Norm Upper Bound of the Inverse Margindouble
productFeatureOperatorNorm()
Compute the Decision Function Entropy Number Upper Bound using the Product of the Feature Space's Norm for the Upper Bound of the Entropy Number and the Scaling Operator NormMethods inherited from class java.lang.Object
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
-
Constructor Details
-
DecisionFunctionOperatorBounds
public DecisionFunctionOperatorBounds(DiagonalScalingOperator dsoFactorizer, double dblInverseMarginNormBound, double dblFeatureSpaceMaureyConstant, int iFeatureSpaceDimension) throws java.lang.ExceptionDecisionFunctionOperatorBounds Constructor- Parameters:
dsoFactorizer
- The Factorizing Diagonal Scaling OperatordblInverseMarginNormBound
- The Decision Function Inverse Margin Norm BounddblFeatureSpaceMaureyConstant
- The Kernel Feature Space Function Maurey ConstantiFeatureSpaceDimension
- The Kernel Feature Space Dimension- Throws:
java.lang.Exception
- Thrown if the Inputs are Invalid
-
-
Method Details
-
factorizingOperator
Retrieve the Factorizing Diagonal Scaling Operator Instance- Returns:
- The Factorizing Diagonal Scaling Operator Instance
-
inverseMarginNormBound
public double inverseMarginNormBound()Retrieve the Norm Upper Bound of the Inverse Margin- Returns:
- The Norm Upper Bound of the Inverse Margin
-
featureSpaceMaureyConstant
public double featureSpaceMaureyConstant()Retrieve the Feature Space Maurey Constant- Returns:
- The Feature Space Maurey Constant
-
featureSpaceDimension
public double featureSpaceDimension()Retrieve the Feature Space Dimension- Returns:
- The Feature Space Dimension
-
featureSpaceMaureyBound
public double featureSpaceMaureyBound(int iFeatureSpaceEntropyNumber) throws java.lang.ExceptionCompute the Feature Space's Maurey Bound for the Entropy Number given the specified Entropy Number- Parameters:
iFeatureSpaceEntropyNumber
- The Feature Space Entropy Number- Returns:
- The Feature Space's Maurey Bound for the specified Entropy Number
- Throws:
java.lang.Exception
- The Feature Space's Maurey Bound cannot be computed
-
featureMaureyOperatorEntropy
public double featureMaureyOperatorEntropy(int iFeatureSpaceEntropyNumber) throws java.lang.ExceptionCompute the Decision Function Entropy Number Upper Bound using the Product of the Feature Space's Maurey Upper Bound for the Entropy for the specified Entropy Number and the Scaling Operator Entropy Number Upper Bound- Parameters:
iFeatureSpaceEntropyNumber
- The Feature Space Entropy Number- Returns:
- The Feature Space's Operator Entropy for the specified Entropy Number
- Throws:
java.lang.Exception
- The Feature Space's Operator Entropy cannot be computed
-
featureMaureyOperatorNorm
public double featureMaureyOperatorNorm(int iFeatureSpaceEntropyNumber) throws java.lang.ExceptionCompute the Decision Function Entropy Number Upper Bound using the Product of the Feature Space's Maurey Upper Bound for the Entropy for the specified Entropy Number and the Scaling Operator Norm- Parameters:
iFeatureSpaceEntropyNumber
- The Feature Space Entropy Number- Returns:
- The Feature Space's Operator Norm for the specified Entropy Number
- Throws:
java.lang.Exception
- The Feature Space's Operator Norm cannot be computed
-
productFeatureOperatorNorm
public double productFeatureOperatorNorm() throws java.lang.ExceptionCompute the Decision Function Entropy Number Upper Bound using the Product of the Feature Space's Norm for the Upper Bound of the Entropy Number and the Scaling Operator Norm- Returns:
- The Entropy Number Upper Bound using the Product Norm
- Throws:
java.lang.Exception
- The Entropy Number Upper Bound cannot be computed
-
featureNormOperatorEntropy
public double featureNormOperatorEntropy() throws java.lang.ExceptionCompute the Decision Function Entropy Number Upper Bound using the Product of the Feature Space's Norm for the Upper Bound of the Entropy Number and the Scaling Operator Entropy Number Upper Bound- Returns:
- The Entropy Number Upper Bound using the Product Norm
- Throws:
java.lang.Exception
- The Entropy Number Upper Bound cannot be computed
-
infimumUpperBound
public double infimumUpperBound(int iFeatureSpaceEntropyNumber) throws java.lang.ExceptionCompute the Infimum of the Decision Function Operator Upper Bound across all the Product Bounds for the specified Feature Space Entropy Number- Parameters:
iFeatureSpaceEntropyNumber
- The specified Feature Space Entropy Number- Returns:
- Infimum of the Decision Function Operator Upper Bound
- Throws:
java.lang.Exception
- Thrown if the Infimum of the Decision Function Operator Upper Bound cannot be calculated
-