Estimate Density Ratio p_nu(x)/p_de(y) by uLSIF (unconstrained Least-Square Importance Fitting)

Share:

Description

Estimate Density Ratio p_nu(x)/p_de(y) by uLSIF (unconstrained Least-Square Importance Fitting)

Usage

1
2
uLSIF(x, y, sigma = 10^seq(-3, 1, length.out = 9), lambda = 10^seq(-3, 1,
  length.out = 9), kernel_num = 100, verbose = TRUE)

Arguments

x

numeric vector or matrix as data from a numerator distribution p_nu(x).

y

numeric vector or matrix as data from a denominator distribution p_de(y).

sigma

positive numeric vector as a search range of Gaussian kernel bandwidth.

lambda

positive numeric vector as a search range of regularization parameter.

kernel_num

positive integer as number of kernels.

verbose

logical(default TRUE).

Value

uLSIF object that contains the function to estimate density ratio.