nosof94exalcove_opt: Parameter optimization of ex-ALCOVE model with nosof94 CIRP

View source: R/nosof94exalcove_opt.R

nosof94exalcove_optR Documentation

Parameter optimization of ex-ALCOVE model with nosof94 CIRP

Description

Uses nosof94exalcove to find best-fitting parameters for the ex-ALCOVE model for the nosof94 CIRP.

Usage


  nosof94exalcove_opt(recompute = FALSE, xtdo = FALSE)

Arguments

recompute

When set to TRUE, the function re-runs the optimization. When set to FALSE, the function returns a stored copy of the results of the optimization.

xtdo

eXTenDed Output; where set to TRUE, some further details of the optimization procedure are printed to the console.

Details

This function is an archive of the optimization procedure used to derive the best-fitting parameters for the nosof94exalcove simulation; see Spicer et al. (2017) for a tutorial introduction to the concept of simulation archives.

Optimization used the L-BFGS-B method from the optim function of the standard R stats package. The objective function was sum of squared errors. Please inspect the source code for further details (e.g. type nosof94exalcove_opt). The optimization was repeated for 15 different sets of starting values.

Where recompute = TRUE, the function can take many hours to run, depending on your system, and there is no progress bar. You can use Task Manager (Windows) or equivalent if you want some kind of visual feedback that the code is working hard. The code uses all the processor cores on the local machine, so speed of execution is a simple function of clock speed times processor cores. So, for example, a 4 GHz i7 processor (8 virutal cores) will take a quarter of the time to run this compared to a 2 GHz i5 processor (4 virtual cores).

Value

A vector containing the best-fitting values for c, phi, la, and lw, in that order. See slpALCOVE for an explanation of these parameters.

Author(s)

Andy Wills

References

Spicer, S., Jones, P.M., Inkster, A.B., Edmunds, C.E.R. & Wills, A.J. (2017). Progress in learning theory through distributed collaboration: Concepts, tools, and examples. Manuscript in preparation.


catlearn documentation built on April 4, 2023, 5:12 p.m.