Timeline for Why do we only see $L_1$ and $L_2$ regularization but not other norms?
Current License: CC BY-SA 3.0
17 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Jun 30, 2017 at 19:48 | history | edited | Paul | CC BY-SA 3.0 |
added 12 characters in body
|
Mar 30, 2017 at 16:57 | comment | added | Firebug | @Olivier Well, referring to $\|\cdot\|_2^2$ as the $\ell_2$-norm is so commonplace in practice and in the literature we sometimes forget it was actually squared to begin with, don't be harsh. | |
Mar 28, 2017 at 18:09 | comment | added | kjetil b halvorsen♦ | It isn't very clear what you want proved ... (will look into it, but now I am travelling ...) | |
Mar 28, 2017 at 17:45 | comment | added | user10024395 | I think I ask in the question for proofs rather than qualitative answer. Is there a reason why almost everyone is giving me qualitative answers? | |
Mar 27, 2017 at 22:42 | comment | added | Olivier | @Firebug Yet the mathematical mumbo-jumbo in whuber's comment has not been corrected... | |
Mar 27, 2017 at 12:40 | comment | added | Firebug | @Olivier Oh, you are actually right. I misunderstood, because the squared $\ell_2$-norm is actually used, and it's differentiable everywhere. | |
Mar 27, 2017 at 12:38 | comment | added | Olivier | @Firebug No. I'm thinking about the $L^2$ norm in 1 dimension, which is there the same as the $L^1$ norm. Am I missing something? | |
Mar 27, 2017 at 11:59 | comment | added | Firebug | @Olivier The $\ell_2$-norm is differentiable at the origin, you are thinking about the $\ell_1$-norm. | |
Mar 26, 2017 at 19:02 | comment | added | Olivier | @kjetilbhalvorsen Can you expand a little on Whuber's comment? It is well known that the $L^2$ norm is not differentiable at the origin (consider $x \mapsto |x|$, for instance). It is not clear either what is meant by 'local equivalence' of norms. References are needed, to say the least. | |
Mar 26, 2017 at 18:54 | history | edited | amoeba | CC BY-SA 3.0 |
deleted 26 characters in body
|
Mar 25, 2017 at 17:30 | comment | added | Ferdi | @kjetilbhalvorsen Thank you for your profound answer. I choose the uncommon superscripting in order to be consistent with the question and the title. Of course you can write it in the way you prefer. | |
Mar 25, 2017 at 17:18 | history | edited | kjetil b halvorsen♦ | CC BY-SA 3.0 |
added 1534 characters in body
|
Mar 25, 2017 at 16:33 | history | edited | kjetil b halvorsen♦ | CC BY-SA 3.0 |
added 351 characters in body
|
S Mar 25, 2017 at 16:27 | history | edited | Carl | CC BY-SA 3.0 |
Hyperlink, Mathjax, proper Formatting
|
S Mar 25, 2017 at 16:27 | history | suggested | Ferdi | CC BY-SA 3.0 |
Hyperlink, Mathjax, proper Formatting
|
Mar 25, 2017 at 16:11 | review | Suggested edits | |||
S Mar 25, 2017 at 16:27 | |||||
Mar 23, 2017 at 17:55 | history | answered | kjetil b halvorsen♦ | CC BY-SA 3.0 |