tf.contrib.kfac.fisher_factors.InverseProvidingFactor

Class InverseProvidingFactor

Inherits From: FisherFactor

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

Base class for FisherFactors that maintain inverses explicitly.

This class explicitly calculates and stores inverses of covariance matrices provided by the underlying FisherFactor implementation. It is assumed that vectors can be represented as 2-D matrices.

Subclasses must implement the _compute_new_cov method, and the _var_scope and _cov_shape properties.

Properties

name

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.

get_eigendecomp

get_eigendecomp()

Creates or retrieves eigendecomposition of self._cov.

get_inverse

get_inverse(damping_func)

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).

left_multiply_matpower

left_multiply_matpower(
    x,
    exp,
    damping_func
)

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_inverse

register_inverse(damping_func)

register_matpower

register_matpower(
    exp,
    damping_func
)

Registers a matrix power to be maintained and served on demand.

This creates a variable and signals make_inverse_update_ops to make the corresponding update op. The variable can be read via the method get_matpower.

Args:

  • exp: float. The exponent to use in the matrix power.
  • damping_func: A function that computes a 0-D Tensor or a float which will be the damping value used. i.e. damping = damping_func().

right_multiply_matpower

right_multiply_matpower(
    x,
    exp,
    damping_func
)