Transform diagonal of [batch-]matrix, leave rest of matrix unchanged.
tf.contrib.distributions.matrix_diag_transform( matrix, transform=None, name=None )
Create a trainable covariance defined by a Cholesky factor:
# Transform network layer into 2 x 2 array. matrix_values = tf.contrib.layers.fully_connected(activations, 4) matrix = tf.reshape(matrix_values, (batch_size, 2, 2)) # Make the diagonal positive. If the upper triangle was zero, this would be a # valid Cholesky factor. chol = matrix_diag_transform(matrix, transform=tf.nn.softplus) # LinearOperatorLowerTriangular ignores the upper triangle. operator = LinearOperatorLowerTriangular(chol)
Example of heteroskedastic 2-D linear regression.
tfd = tfp.distributions # Get a trainable Cholesky factor. matrix_values = tf.contrib.layers.fully_connected(activations, 4) matrix = tf.reshape(matrix_values, (batch_size, 2, 2)) chol = matrix_diag_transform(matrix, transform=tf.nn.softplus) # Get a trainable mean. mu = tf.contrib.layers.fully_connected(activations, 2) # This is a fully trainable multivariate normal! dist = tfd.MultivariateNormalTriL(mu, chol) # Standard log loss. Minimizing this will "train" mu and chol, and then dist # will be a distribution predicting labels as multivariate Gaussians. loss = -1 * tf.reduce_mean(dist.log_prob(labels))
R >= 2, where the last two dimensions are equal.
transform: Element-wise function mapping
Tensors. To be applied to the diagonal of
matrixis returned unchanged. Defaults to
name: A name to give created ops. Defaults to "matrix_diag_transform".
Tensor with same shape and