Class Lamb


public final class Lamb extends Optimizer
LAMB (You et al., 2020): Adam's bias-corrected update plus decoupled weight decay, scaled per parameter by the trust ratio |p| / |update|.
  • Constructor Details

    • Lamb

      public Lamb(List<Tensor> params, float lr, float beta1, float beta2, float eps, float weightDecay)
      LAMB with the given betas, eps and decoupled weight decay.
  • 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