gaussian_grad_v: Gradient of Bregman Loss in Gaussian Case with respect to v

Description Usage Arguments Value

Description

Gradient of Bregman Loss in Gaussian Case with respect to v

Usage

1
gaussian_grad_v(x, a, v, s, lambda, mu0)

Arguments

x

A single row of column of x, for which we want to minimize distance to the mean.

a

Either a vector or scale representing the latent scores.

v

Either a vector or scale representing the latent loadings.

s

Either the s^th row or column of the matrix AV^T - a_cv_c^T

lambda

The regularization parameter in the optimization.

mu0

The value to regularize towards.

Value

The value of the gradient of the bregman loss with respect to the parameter v.


krisrs1128/expPCA documentation built on May 20, 2019, 1:26 p.m.