tf.contrib.kfac.fisher_factors.DiagonalFactor

Class DiagonalFactor

Inherits From: FisherFactor

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

A base class for FisherFactors that use diagonal approximations.

A DiagonalFactor's covariance variable can be of any shape, but must contain exactly one entry per parameter.

Methods

__init__

__init__()

get_cov

get_cov()

get_cov_var

get_cov_var()

Get variable backing this FisherFactor.

May or may not be the same as self.get_cov()

Returns:

Variable of shape self._cov_shape.

instantiate_covariance

instantiate_covariance()

Instantiates the covariance Variable as the instance member _cov.

left_multiply

left_multiply(
    x,
    damping
)

left_multiply_inverse

left_multiply_inverse(
    x,
    damping
)

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()

register_damped_inverse

register_damped_inverse(damping)

right_multiply

right_multiply(
    x,
    damping
)

right_multiply_inverse

right_multiply_inverse(
    x,
    damping
)