Package org.drip.learning.bound

Covering Numbers, Concentration, Lipschitz Bounds

Author:

Lakshmi Krishnamurthy

Class Summary

Class	Description
CoveringNumberBoundBuilder	CoveringNumberBoundBuilder constructs the CoveringNumberProbabilityBound Instances for specific Learning Situations.
CoveringNumberLossBound	CoveringNumberLossBound provides the Upper Probability Bound that the Loss/Deviation of the Empirical from the Actual Mean of the given Learner Class exceeds 'epsilon', using the Covering Number Generalization Bounds.
DiagonalOperatorCoveringBound	DiagonalOperatorCoveringBound implements the Behavior of the Bound on the Covering Number of the Diagonal Scaling Operator.
EmpiricalLearnerLoss	EmpiricalLearnerLoss Function computes the Empirical Loss of a Learning Operation resulting from the Use of a Learning Function in Conjunction with the corresponding Empirical Realization.
LipschitzCoveringNumberBound	LipschitzCoveringNumberBound contains the Upper Bounds of the Covering Numbers induced by Lipschitz and approximate Lipschitz Loss Function Class.
MeasureConcentrationExpectationBound	MeasureConcentrationExpectationBound provides the Upper Bound of the Expected Loss between Empirical Outcome and the Prediction of the given Learner Class using the Concentration of Measure Inequalities.