jax.numpy.logaddexp2#

jax.numpy.logaddexp2(x1, x2) = <jax._src.custom_derivatives.custom_jvp object>[source]#

Logarithm of the sum of exponentiations of the inputs in base-2.

LAX-backend implementation of numpy.logaddexp2().

Original docstring below.

Calculates log2(2**x1 + 2**x2). This function is useful in machine learning when the calculated probabilities of events may be so small as to exceed the range of normal floating point numbers. In such cases the base-2 logarithm of the calculated probability can be used instead. This function allows adding probabilities stored in such a fashion.

Parameters
  • x1 (array_like) – Input values. If x1.shape != x2.shape, they must be broadcastable to a common shape (which becomes the shape of the output).

  • x2 (array_like) – Input values. If x1.shape != x2.shape, they must be broadcastable to a common shape (which becomes the shape of the output).

  • out (ndarray, None, or tuple of ndarray and None, optional) – A location into which the result is stored. If provided, it must have a shape that the inputs broadcast to. If not provided or None, a freshly-allocated array is returned. A tuple (possible only as a keyword argument) must have length equal to the number of outputs.

Returns

result – Base-2 logarithm of 2**x1 + 2**x2. This is a scalar if both x1 and x2 are scalars.

Return type

ndarray