Optimizers

Dictionary of torch optimizers. Use t_opt for conveniently retrieving optimizers. Can be converted to a data.table using as.data.table.

Usage

mlr3torch_optimizers

Format

An object of class DictionaryMlr3torchOptimizers (inherits from Dictionary, R6) of length 13.

Available Optimizers

adadelta, adagrad, adam, asgd, rmsprop, rprop, sgd

See also

Other Torch Descriptor: TorchCallback, TorchDescriptor, TorchLoss, TorchOptimizer, as_torch_callbacks(), as_torch_loss(), as_torch_optimizer(), mlr3torch_losses, t_clbk(), t_loss(), t_opt()

Other Dictionary: mlr3torch_callbacks, mlr3torch_losses, t_opt()

Examples

mlr3torch_optimizers$get("adam")
#> <TorchOptimizer:adam> Adaptive Moment Estimation
#> * Generator: optim_adam
#> * Parameters: list()
#> * Packages: torch,mlr3torch
# is equivalent to
t_opt("adam")
#> <TorchOptimizer:adam> Adaptive Moment Estimation
#> * Generator: optim_adam
#> * Parameters: list()
#> * Packages: torch,mlr3torch
# convert to a data.table
as.data.table(mlr3torch_optimizers)
#> Key: <key>
#>         key                         label        packages
#>      <char>                        <char>          <char>
#> 1: adadelta Adaptive Learning Rate Method torch,mlr3torch
#> 2:  adagrad   Adaptive Gradient algorithm torch,mlr3torch
#> 3:     adam    Adaptive Moment Estimation torch,mlr3torch
#> 4:     asgd  SGD with Adaptive Batch Size torch,mlr3torch
#> 5:  rmsprop  Root Mean Square Propagation torch,mlr3torch
#> 6:    rprop     Resilient Backpropagation torch,mlr3torch
#> 7:      sgd   Stochastic Gradient Descent torch,mlr3torch