Timeline for Understanding the tradeoff with regularization in SVMs
Current License: CC BY-SA 3.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 1, 2016 at 16:03 | history | edited | gung - Reinstate Monica | CC BY-SA 3.0 |
light editing
|
| Apr 25, 2014 at 7:36 | history | edited | Marc Claesen | CC BY-SA 3.0 |
added 29 characters in body
|
| Apr 25, 2014 at 7:32 | comment | added | Marc Claesen | @CodeKingPlusPlus I've added an example to clarify things. | |
| Apr 25, 2014 at 7:31 | history | edited | Marc Claesen | CC BY-SA 3.0 |
added 1391 characters in body
|
| Apr 25, 2014 at 7:25 | history | edited | Marc Claesen | CC BY-SA 3.0 |
added 1391 characters in body
|
| Apr 25, 2014 at 1:50 | comment | added | CodeKingPlusPlus | Can you explain what you mean by 'balance,' I think that is the key idea I am missing. | |
| Apr 24, 2014 at 6:52 | comment | added | Marc Claesen | @CodeKingPlusPlus no, since $\lambda$ can range from $0$ to $\infty$ you can have any balance you want. In the extreme cases you are only minimizing a single term. | |
| Apr 24, 2014 at 0:34 | comment | added | CodeKingPlusPlus | Writing it this way makes it seem like you can only minimize either $||w||^2$ or $\lambda\sum\limits_{i=1}^T \epsilon_i$. Is this the case? | |
| Apr 23, 2014 at 20:47 | history | edited | Marc Claesen | CC BY-SA 3.0 |
added 110 characters in body
|
| Apr 23, 2014 at 20:42 | history | answered | Marc Claesen | CC BY-SA 3.0 |