Adamax optimizer

    Adamax optimizer from Section 7 of the Adam paper. It is a variant of Adam based on the infinity norm.

    optimizer_adamax(
      lr = 0.002,
      beta_1 = 0.9,
      beta_2 = 0.999,
      epsilon = NULL,
      decay = 0,
      clipnorm = NULL,
      clipvalue = NULL
    )

    Arguments

    lr

    float >= 0. Learning rate.

    beta_1

    The exponential decay rate for the 1st moment estimates. float, 0 < beta < 1. Generally close to 1.

    beta_2

    The exponential decay rate for the 2nd moment estimates. float, 0 < beta < 1. Generally close to 1.

    epsilon

    float >= 0. Fuzz factor. If NULL, defaults to k_epsilon().

    decay

    float >= 0. Learning rate decay over each update.

    clipnorm

    Gradients will be clipped when their L2 norm exceeds this value.

    clipvalue

    Gradients will be clipped when their absolute value exceeds this value.

    See also