Skip to contents

Alternating optimization

The ao package implements alternating optimization in R.

Alternating optimization is an iterative procedure which optimizes a function jointly over all parameters by alternately performing restricted optimization over individual parameter subsets.

For additional details on the method, please refer to the package vignette.

Installation

You can install the released version from CRAN with:

And the development version from GitHub with:

# install.packages("devtools")
devtools::install_github("loelschlaeger/ao")

Example

The following is a simple example to perform alternating optimization of the Himmelblau’s function, separately for x1 and x2, with the parameter restrictions  − 5 ≤ x1, x2 ≤ 5:

library("ao")
himmelblau <- function(x) (x[1]^2 + x[2] - 11)^2 + (x[1] + x[2]^2 - 7)^2
ao(
  f = himmelblau, p = c(0, 0), partition = list(1, 2),
  base_optimizer = optimizer_optim(lower = -5, upper = 5, method = "L-BFGS-B")
)
#> $value
#> [1] 1.940035e-12
#> 
#> $estimate
#> [1]  3.584428 -1.848126
#> 
#> $sequence
#>    iteration partition        value      seconds       p1        p2
#> 1          0        NA 1.700000e+02 0.000000e+00 0.000000  0.000000
#> 2          1         1 1.327270e+01 2.765894e-03 3.395691  0.000000
#> 3          1         2 1.743666e+00 1.089573e-04 3.395691 -1.803183
#> 4          2         1 2.847292e-02 8.606911e-05 3.581412 -1.803183
#> 5          2         2 4.687472e-04 7.295609e-05 3.581412 -1.847412
#> 6          3         1 7.368063e-06 9.822845e-05 3.584381 -1.847412
#> 7          3         2 1.157612e-07 5.006790e-05 3.584381 -1.848115
#> 8          4         1 1.900153e-09 5.292892e-05 3.584427 -1.848115
#> 9          4         2 4.221429e-11 4.196167e-05 3.584427 -1.848126
#> 10         5         1 3.598278e-12 3.981590e-05 3.584428 -1.848126
#> 11         5         2 1.940035e-12 4.601479e-05 3.584428 -1.848126
#> 
#> $seconds
#> [1] 0.003362894

Contact

Have a question, found a bug, request a feature, want to contribute? Please file an issue.