org.drip.learning.bound

Class CoveringNumberBoundBuilder

java.lang.Object

org.drip.learning.bound.CoveringNumberBoundBuilder

public class CoveringNumberBoundBuilder
extends java.lang.Object

CoveringNumberBoundBuilder constructs the CoveringNumberProbabilityBound Instances for specific Learning Situations. The References are: 1) Alon, N., S. Ben-David, N. Cesa Bianchi, and D. Haussler (1997): Scale-sensitive Dimensions, Uniform Convergence, and Learnability, Journal of Association of Computational Machinery, 44 (4) 615-631. 2) Anthony, M., and P. L. Bartlett (1999): Artificial Neural Network Learning - Theoretical Foundations, Cambridge University Press, Cambridge, UK. 3) Kearns, M. J., R. E. Schapire, and L. M. Sellie (1994): Towards Efficient Agnostic Learning, Machine Learning, 17 (2) 115-141. 4) Lee, W. S., P. L. Bartlett, and R. C. Williamson (1998): The Importance of Convexity in Learning with Squared Loss, IEEE Transactions on Information Theory, 44 1974-1980. 5) Vapnik, V. N. (1998): Statistical learning Theory, Wiley, New York.

Author:

Lakshmi Krishnamurthy

Field Summary

Fields

Modifier and Type	Field and Description
static double	EPSILON_EXPONENT_AGNOSTIC_CONVEX_LEARNING Epsilon Exponent for Agnostic Learning with Convex Functions
static double	EPSILON_EXPONENT_AGNOSTIC_LEARNING Epsilon Exponent for Agnostic Learning
static double	EPSILON_EXPONENT_REGRESSION_LEARNING Epsilon Exponent for Regression Learning

Constructor Summary

Constructors

Constructor and Description
CoveringNumberBoundBuilder()

Method Summary

Modifier and Type	Method and Description
static CoveringNumberLossBound	AgnosticConvexLearning(R1ToR1 funcSampleCoefficient, double dblExponentScaler) Construct the Agnostic Convex Learning CoveringNumberProbabilityBound Instance
static CoveringNumberLossBound	AgnosticLearning(R1ToR1 funcSampleCoefficient, double dblExponentScaler) Construct the Agnostic Learning CoveringNumberProbabilityBound Instance
static CoveringNumberLossBound	RegressionLearning(R1ToR1 funcSampleCoefficient, double dblExponentScaler) Construct the Regression Learning CoveringNumberProbabilityBound Instance

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

EPSILON_EXPONENT_REGRESSION_LEARNING

public static final double EPSILON_EXPONENT_REGRESSION_LEARNING

Epsilon Exponent for Regression Learning

See Also:

Constant Field Values

EPSILON_EXPONENT_AGNOSTIC_LEARNING

public static final double EPSILON_EXPONENT_AGNOSTIC_LEARNING

Epsilon Exponent for Agnostic Learning

See Also:

Constant Field Values

EPSILON_EXPONENT_AGNOSTIC_CONVEX_LEARNING

public static final double EPSILON_EXPONENT_AGNOSTIC_CONVEX_LEARNING

Epsilon Exponent for Agnostic Learning with Convex Functions

See Also:

Constant Field Values

Constructor Detail

CoveringNumberBoundBuilder

public CoveringNumberBoundBuilder()

Method Detail

RegressionLearning

public static final CoveringNumberLossBound RegressionLearning(R1ToR1 funcSampleCoefficient,
                                                               double dblExponentScaler)

Construct the Regression Learning CoveringNumberProbabilityBound Instance

Parameters:

funcSampleCoefficient - The Sample Coefficient Function

dblExponentScaler - The Exponent Scaler

Returns:

The Regression Learning CoveringNumberProbabilityBound Instance

AgnosticLearning

public static final CoveringNumberLossBound AgnosticLearning(R1ToR1 funcSampleCoefficient,
                                                             double dblExponentScaler)

Construct the Agnostic Learning CoveringNumberProbabilityBound Instance

Parameters:

funcSampleCoefficient - The Sample Coefficient Function

dblExponentScaler - The Exponent Scaler

Returns:

The Agnostic Learning CoveringNumberProbabilityBound Instance

AgnosticConvexLearning

public static final CoveringNumberLossBound AgnosticConvexLearning(R1ToR1 funcSampleCoefficient,
                                                                   double dblExponentScaler)

Construct the Agnostic Convex Learning CoveringNumberProbabilityBound Instance

Parameters:

funcSampleCoefficient - The Sample Coefficient Function

dblExponentScaler - The Exponent Scaler

Returns:

The Agnostic Convex Learning CoveringNumberProbabilityBound Instance