distributions.py 文件源码

def gaus_posterior(dim, std0):
    """Initialise a posterior Gaussian distribution with a diagonal covariance.

    Even though this is initialised with a diagonal covariance, a full
    covariance will be learned, using a lower triangular Cholesky
    parameterisation.

    Parameters
    ----------
    dim : tuple or list
        the dimension of this distribution.
    std0 : float
        the initial (unoptimized) diagonal standard deviation of this
        distribution.

    Returns
    -------
    Q : tf.contrib.distributions.MultivariateNormalTriL
        the initialised posterior Gaussian object.

    Note
    ----
    This will make tf.Variables on the randomly initialised mean and covariance
    of the posterior. The initialisation of the mean is from a Normal with zero
    mean, and ``std0`` standard deviation, and the initialisation of the (lower
    triangular of the) covariance is from a gamma distribution with an alpha of
    ``std0`` and a beta of 1.

    """
    o, i = dim

    # Optimize only values in lower triangular
    u, v = np.tril_indices(i)
    indices = (u * i + v)[:, np.newaxis]
    l0 = np.tile(np.eye(i), [o, 1, 1])[:, u, v].T
    l0 = l0 * tf.random_gamma(alpha=std0, shape=l0.shape, seed=next(seedgen))
    lflat = tf.Variable(l0, name="W_cov_q")
    Lt = tf.transpose(tf.scatter_nd(indices, lflat, shape=(i * i, o)))
    L = tf.reshape(Lt, (o, i, i))

    mu_0 = tf.random_normal((o, i), stddev=std0, seed=next(seedgen))
    mu = tf.Variable(mu_0, name="W_mu_q")
    Q = MultivariateNormalTriL(mu, L)
    return Q


#
# KL divergence calculations
#