tfmri.convex.ConvexFunctionNorm

class ConvexFunctionNorm(domain_dimension, order, scale=None, dtype=None, name=None)[source]

Bases: tensorflow_mri.python.ops.convex_ops.ConvexFunction

A ConvexFunction computing the [scaled] Lp-norm of a [batch of] inputs.

Parameters

  • domain_dimension – A scalar integer tf.Tensor. The dimension of the domain.

  • order – A float. The order of the norm. Supported values are 1, 2, np.inf.

  • scale –

    A float. A scaling factor. Defaults to 1.0.

  • dtype – A tf.dtypes.DType. The type of this ConvexFunction. Defaults to tf.dtypes.float32.

  • name – A name for this ConvexFunction.

References

1

Parikh, N., & Boyd, S. (2014). Proximal algorithms. Foundations and Trends in optimization, 1(3), 127-239.

Initialize this ConvexFunction.