tf.contrib.kfac.fisher_factors.NaiveDiagonalFactor

Class NaiveDiagonalFactor

Inherits From: DiagonalFactor

Defined in tensorflow/contrib/kfac/python/ops/fisher_factors.py.

FisherFactor for a diagonal approximation of any type of param's Fisher.

Note that this uses the naive "square the sum estimator", and so is applicable to any type of parameter in principle, but has very high variance.

Properties

name

Methods

__init__

__init__(
    params_grads,
    batch_size
)

Initializes NaiveDiagonalFactor instance.

Args:

  • params_grads: Sequence of Tensors, each with same shape as parameters this FisherFactor corresponds to. For example, the gradient of the loss with respect to parameters.
  • batch_size: int or 0-D Tensor. Size

get_cholesky

get_cholesky(damping_func)

get_cholesky_inverse

get_cholesky_inverse(damping_func)

get_cov

get_cov()

get_cov_as_linear_operator

get_cov_as_linear_operator()

get_matpower

get_matpower(
    exp,
    damping_func
)

instantiate_cov_variables

instantiate_cov_variables()

Makes the internal cov variable(s).

instantiate_inv_variables

instantiate_inv_variables()

Makes the internal "inverse" variable(s).

make_covariance_update_op

make_covariance_update_op(ema_decay)

Constructs and returns the covariance update Op.

Args:

  • ema_decay: The exponential moving average decay (float or Tensor).

Returns:

An Op for updating the covariance Variable referenced by _cov.

make_inverse_update_ops

make_inverse_update_ops()

Create and return update ops corresponding to registered computations.

register_cholesky

register_cholesky(damping_func)

register_cholesky_inverse

register_cholesky_inverse(damping_func)

register_matpower

register_matpower(
    exp,
    damping_func
)