vaeac_get_optimizer: Function to create the optimizer used to train 'vaeac'

In NorskRegnesentral/shapr: Prediction Explanation with Dependence-Aware Shapley Values

Function to create the optimizer used to train vaeac

Description

Only torch::optim_adam() is currently supported. But it is easy to add an additional option later.

Usage

vaeac_get_optimizer(vaeac_model, lr, optimizer_name = "adam")

Arguments

vaeac_model	A vaeac model created using vaeac().
lr	Positive numeric (default is 0.001). The learning rate used in the torch::optim_adam() optimizer.
optimizer_name	String containing the name of the torch::optimizer() to use.

Value

A torch::optim_adam() optimizer connected to the parameters of the vaeac_model.

Author(s)

Lars Henry Berge Olsen

NorskRegnesentral/shapr documentation built on April 19, 2024, 1:19 p.m.