get_k: get_k

In mrecos/klrfome: Kernel Logistic Regression with Focal Mean Embeddings

get_k

Description

'get_k()' is an internal function used by 'build_k()' to calcualte similarity kernel for each pair of observations

Usage

get_k(y1, y2, sigma, dist_metric = "euclidean")

Arguments

y1	- [NxP] Matrix of data from bag i
y2	- [NxP] Matrix of data from bag j
sigma	- [scaler] smoothing hyperparameters for RBF kernel
dist_metric	[character] One of the distance methods from rdist::cdist. Default = "euclidean". see ?rdist::cdist

Details

This function takes two data.frames or matricies, calculates the cross distance between them, and then applies a radial basis function to the resulting distance matrix.

Value

Matrix G

mrecos/klrfome documentation built on April 6, 2022, 8:02 p.m.