Stochastic#
An optimizer based on vanilla Stochastic Gradient Descent that takes a step proportional to the rate supplied by its learning-rate schedule.
Parameters#
| # | Name | Default | Type | Description |
|---|---|---|---|---|
| 1 | scheduler | Scheduler | The learning-rate schedule that supplies the step size each batch. |
Example#
use Rubix\ML\NeuralNet\Optimizers\Stochastic;
use Rubix\ML\NeuralNet\Optimizers\Schedulers\Constant;
$optimizer = new Stochastic(scheduler: new Constant(0.01));