mapXy.gr.sigmoid: Sigmoid Map Function Gradient

In DPpack: Differentially Private Statistical Analysis and Machine Learning

Sigmoid Map Function Gradient

Description

This function implements the gradient of the sigmoid map function with respect to coeff used for logistic regression in the form required by EmpiricalRiskMinimizationDP.CMS.

Usage

mapXy.gr.sigmoid(X, coeff)

Arguments

X	Matrix of data.
coeff	Vector or matrix of coefficients or weights.

Value

Matrix of values of the gradient of the sigmoid function with respect to each value of coeff.

Examples

  X <- matrix(c(1,2,3,4,5,6),nrow=2)
  coeff <- c(0.5,-1,2)
  mapXy.gr.sigmoid(X,coeff)

DPpack documentation built on Oct. 20, 2024, 9:07 a.m.