Talk:Smooth maximum: Difference between revisions
→LogSumExp: new section |
|||
Line 9: | Line 9: | ||
== LogSumExp == |
== LogSumExp == |
||
The article claims that LogSumExp is a smooth maximum, but this is a category error, since we have defined a smooth maximum to be a *family* of functions, rather than a single function. There is no discussion on how we can parameterize LogSumExp to get a better approximation to the maximum function. |
The article claims that LogSumExp is a smooth maximum, but this is a category error, since we have defined a smooth maximum to be a *family* of functions, rather than a single function. There is no discussion on how we can parameterize LogSumExp to get a better approximation to the maximum function. <small><span style="border:1px solid black;padding:1px;">[[User:J.Gowers|<font style="color:white;background:blue;font-family:sans-serif;">''' J.Gowers '''</font>]]</span></small> 12:47, 2 January 2020 (UTC) |
Revision as of 12:47, 2 January 2020
Mathematics C‑class Mid‑priority | ||||||||||
|
this page needs good references to generalized mean, theoretical & implementation details, uses and possible links back to the softmax function. So far only John Cook's blog posts seem to be useful, http://www.johndcook.com/blog/2010/01/13/soft-maximum/. He does however use a different function that converges in the limit and call the topic soft maximum.
definition according to who?
The article gives a definition of a smooth maximum in general - a category of functions that must fulfil some criteria - but does not say who gave this definition, or who uses it, or why this definition might exist. Is it real? Is there supporting literature?--mcld (talk) 15:33, 8 March 2017 (UTC)
LogSumExp
The article claims that LogSumExp is a smooth maximum, but this is a category error, since we have defined a smooth maximum to be a *family* of functions, rather than a single function. There is no discussion on how we can parameterize LogSumExp to get a better approximation to the maximum function. J.Gowers 12:47, 2 January 2020 (UTC)