Smooth maximum
In mathematics, a smooth maximum of an indexed family x1, ..., xn of numbers is a differentiable approximation to the maximum function
and the concept of smooth minimum is similarly defined.
Examples
For large positive values of the parameter , the following formulation is one smooth, differentiable approximation of the maximum function. For negative values of the parameter that are large in absolute value, it approximates the minimum.
has the following properties:
- as
- is the arithmetic mean of its inputs
- as
The gradient of is closely related to softmax and is given by
This makes the softmax function useful for optimization techniques that use gradient descent.
LogSumExp
Another smooth maximum is LogSumExp:
This can also be normalized if the are all non-negative, yielding a function with domain and range :
The term corrects for the fact that by canceling out all but one zero exponential, and if all are zero.
See also
References
M. Lange, D. Zühlke, O. Holz, and T. Villmann, "Applications of lp-norms and their smooth approximations for gradient based learning vector quantization," in Proc. ESANN, Apr. 2014, pp. 271-276. (https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2014-153.pdf)