def adam()

in optim.py [0:0]

• 28 lines of code
• 5 McCabe index (conditional complexity)

def adam(params, cost_or_grads, alpha=3e-4, hps=None, epsilon=1e-8):
    updates = []
    if type(cost_or_grads) is not list:
        gs = tf.gradients(cost_or_grads, params)
    else:
        gs = cost_or_grads

    beta2 = 1-1./(hps.train_its*hps.polyak_epochs)

    # all-reduce
    grads = [Z.allreduce_mean(g) for g in gs]

    t = tf.Variable(1., 'adam_t')
    alpha_t = alpha * tf.sqrt((1. - tf.pow(beta2, t))) / \
        (1. - tf.pow(hps.beta1, t))
    updates.append(t.assign_add(1))

    for w, g in zip(params, grads):
        mom2 = tf.Variable(tf.zeros(w.get_shape()), w.name + '_adam_m2')
        if hps.beta1 > 0:
            mom1 = tf.Variable(tf.zeros(w.get_shape()), w.name + '_adam_m1')
            mom1_new = hps.beta1 * mom1 + (1. - hps.beta1) * g
            updates.append(mom1.assign(mom1_new))
        else:
            mom1_new = g
        m2_new = beta2 * mom2 + (1. - beta2) * tf.square(g)
        delta_t = mom1_new / (tf.sqrt(m2_new) + epsilon)
        w_new = hps.weight_decay * w - alpha_t * delta_t
        updates.append(mom2.assign(m2_new))
        updates.append(w.assign(w_new))

    # Polyak averaging
    polyak_avg_op, polyak_swap_op, ema = polyak(params, beta2)
    train_op = tf.group(polyak_avg_op, *updates)
    return train_op, polyak_swap_op, ema