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 12.

Available Optimizers

adagrad, adam, adamw, rmsprop, 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_ignite_adam
#> * Parameters: list()
#> * Packages: torch,mlr3torch
# is equivalent to
t_opt("adam")
#> <TorchOptimizer:adam> Adaptive Moment Estimation
#> * Generator: optim_ignite_adam
#> * Parameters: list()
#> * Packages: torch,mlr3torch
# convert to a data.table
as.data.table(mlr3torch_optimizers)
#> Key: <key>
#>        key                                 label        packages
#>     <char>                                <char>          <list>
#> 1: adagrad           Adaptive Gradient algorithm torch,mlr3torch
#> 2:    adam            Adaptive Moment Estimation torch,mlr3torch
#> 3:   adamw Decoupled Weight Decay Regularization torch,mlr3torch
#> 4: rmsprop          Root Mean Square Propagation torch,mlr3torch
#> 5:     sgd           Stochastic Gradient Descent torch,mlr3torch