W3cubDocs

/TensorFlow Python

tf.contrib.kfac.fisher_blocks.compute_pi_tracenorm 

tf.contrib.kfac.fisher_blocks.compute_pi_tracenorm(
    left_cov,
    right_cov
)

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

Computes the scalar constant pi for Tikhonov regularization/damping.

$$\pi = \sqrt{ (trace(A) / dim(A)) / (trace(B) / dim(B)) }$$

See section 6.3 of https://arxiv.org/pdf/1503.05671.pdf for details.

Args:

  • left_cov: The left Kronecker factor "covariance".
  • right_cov: The right Kronecker factor "covariance".

Returns:

The computed scalar constant pi for these Kronecker Factors (as a Tensor).

© 2018 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/tf/contrib/kfac/fisher_blocks/compute_pi_tracenorm