Class AdaGrad

java.lang.Object
ai.beestream.jitnn.nn.optim.Optimizer
ai.beestream.jitnn.nn.optim.AdaGrad

public final class AdaGrad extends Optimizer
AdaGrad (Duchi et al.), PyTorch's semantics: learning-rate decay, L2 weight decay, initial accumulator.
  • Constructor Details

    • AdaGrad

      public AdaGrad(List<Tensor> params, float lr, float lrDecay, float weightDecay, float initialAccumulator, float eps)
      AdaGrad with learning-rate decay, L2 weight decay, the accumulator's starting value, and eps.
  • Method Details

    • step

      public void step()
      Description copied from class: Optimizer
      Records one update of every parameter that has a gradient.
      Specified by:
      step in class Optimizer
    • state

      protected Map<String,Tensor[]> state()
      Description copied from class: Optimizer
      Per-parameter state by slot name, each array indexed like the parameters (null where none).
      Overrides:
      state in class Optimizer