Function adadelta

code/lstm.py:241–299

An adaptive learning rate optimizer Parameters ---------- lr : Theano SharedVariable Initial learning rate tpramas: Theano SharedVariable Model parameters grads: Theano variable Gradients of cost w.r.t to parameres x: Theano variable Mode

(lr, tparams, grads, x, mask, y, cost)

def adadelta(lr, tparams, grads, x, mask, y, cost):
    """
    An adaptive learning rate optimizer

    Parameters
    ----------
    lr : Theano SharedVariable
        Initial learning rate
    tpramas: Theano SharedVariable
        Model parameters
    grads: Theano variable
        Gradients of cost w.r.t to parameres
    x: Theano variable
        Model inputs
    mask: Theano variable
        Sequence mask
    y: Theano variable
        Targets
    cost: Theano variable
        Objective fucntion to minimize

    Notes
    -----
    For more information, see [ADADELTA]_.

    .. [ADADELTA] Matthew D. Zeiler, *ADADELTA: An Adaptive Learning
       Rate Method*, arXiv:1212.5701.
    """

    zipped_grads = [theano.shared(p.get_value() * numpy_floatX(0.),
                                  name='%s_grad' % k)
                    for k, p in tparams.items()]
    running_up2 = [theano.shared(p.get_value() * numpy_floatX(0.),
                                 name='%s_rup2' % k)
                   for k, p in tparams.items()]
    running_grads2 = [theano.shared(p.get_value() * numpy_floatX(0.),
                                    name='%s_rgrad2' % k)
                      for k, p in tparams.items()]

    zgup = [(zg, g) for zg, g in zip(zipped_grads, grads)]
    rg2up = [(rg2, 0.95 * rg2 + 0.05 * (g ** 2))
             for rg2, g in zip(running_grads2, grads)]

    f_grad_shared = theano.function([x, mask, y], cost, updates=zgup + rg2up,
                                    name='adadelta_f_grad_shared')

    updir = [-tensor.sqrt(ru2 + 1e-6) / tensor.sqrt(rg2 + 1e-6) * zg
             for zg, ru2, rg2 in zip(zipped_grads,
                                     running_up2,
                                     running_grads2)]
    ru2up = [(ru2, 0.95 * ru2 + 0.05 * (ud ** 2))
             for ru2, ud in zip(running_up2, updir)]
    param_up = [(p, p + ud) for p, ud in zip(tparams.values(), updir)]

    f_update = theano.function([lr], [], updates=ru2up + param_up,
                               on_unused_input='ignore',
                               name='adadelta_f_update')