f3dasm_optimize.adam#

adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-07, eps_root=0.0, seed=None, **kwargs)[source]#

Adam optimizer. Adapted from the Optax library.

Parameters:

  • learning_rate (float, optional) – The learning rate, by default 0.001.

  • beta_1 (float, optional) – Exponential decay rate for the first moment estimates, by default 0.9.

  • beta_2 (float, optional) – Exponential decay rate for the second moment estimates, by default 0.999.

  • epsilon (float, optional) – A small constant for numerical stability, by default 1e-07.

  • eps_root (float, optional) – A small constant for numerical stability, by default 0.0.

  • seed (int, optional) – Random seed, by default None.

Returns:

Optimizer object.

Return type:

Optimizer