mistnet_fit_optimx: Optimize a mistnet model using the 'optimx' package

In davharris/mistnet2: Neural Networks with Latent Random Variables

Description

Optimize a mistnet model using the optimx package

Usage

mistnet_fit_optimx(network, fn, gr, method = "L-BFGS-B", itnmax = 1000,
  control = list(maximize = TRUE, starttests = FALSE), hessian = FALSE, ...)

Arguments

network	A network object, as produced by the mistnet function
fn	A function of par that returns a scalar describing the (penalized) log-likelihood
gr	A function of par that returns a vector containing the gradient of the (penalized) log-likelihood with respect to all the parameters in par.
method	The name of one method used by optimx. By default, this is "L-BFGS-B", which uses second-order information without approximating the full (inverse) Hessian matrix, which could be very large for some networks. Note that the use of multiple methods is not currently supported.
itnmax, control, hessian	Additional arguments passed to optimx
...	Additional arguments passed to optimx

davharris/mistnet2 documentation built on May 14, 2019, 9:28 p.m.