Regarding nnet package's optimization method 'BFGS'

Hello everyone,

I am using nnet in caret. The nnet document shows that the package uses BFGS optimization method (page no. 5, last line of documentation).

  1. Where can find the details the BFGS, particularly the learning rate/step size?
  2. How is it different from optimization method in Keras R such as SGD, adam, rmsprop ?


myControl <- caret::trainControl(## n-fold CV
method = "repeatedcv",
number = 5,
repeats = 1,
verboseIter = TRUE)

nnGrid <- expand.grid(size =5,
decay = seq(0, 0.6, 0.1))

nnetFit <- caret::train(choice ~ .,
data = tbl,
method = "nnet",
tuneGrid = nnGrid,
trace = FALSE,
maxit = 1000,
trControl = myControl)

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.