Timeline for Smoothing L1 norm, Huber vs Conjugate
Current License: CC BY-SA 3.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 8, 2013 at 10:16 | vote | accept | digdug | ||
| Jan 8, 2013 at 9:51 | answer | added | Dirk | timeline score: 4 | |
| Jan 8, 2013 at 8:32 | history | edited | Pietro Majer | CC BY-SA 3.0 |
(link)
|
| Jan 8, 2013 at 7:18 | comment | added | András Bátkai | @Dirk: why don't you write an answer about these? What you write here might interest more people. | |
| Jan 8, 2013 at 7:15 | comment | added | Dirk | Smoothing the dual will not give you a smooth primal. However, you get a strongly convex primal by dual smoothing (as opposed to merely a strictly convex primal by Huber smoothing). Hence, it depends on what kind of regularity you are aiming at: A smoother primal or a "more convex" primal - both can be helpful algorithmically. Moreover, note that there are numerous methods to treat nonsmooth convex minimization problems efficiently. | |
| Jan 8, 2013 at 4:36 | history | asked | digdug | CC BY-SA 3.0 |