Timeline for Is it possible to “solve” iterative (convex/non-convex) optimization problems via learning (one-shot)?
Current License: CC BY-SA 4.0
14 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 16, 2018 at 19:31 | answer | added | Dirk | timeline score: 1 | |
| Dec 16, 2018 at 18:52 | history | edited | user550103 | CC BY-SA 4.0 |
added 638 characters in body
|
| Dec 4, 2018 at 4:03 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Nov 4, 2018 at 11:18 | comment | added | user550103 | @Suvrit yes exactly. I am seeking such techniques that can "solve" (best approximation possible in some sense) such optimization problems by "learning". Can you guide me with such possibilities that are promising avenues (in your opinion)? Thank you in advance. | |
| Nov 4, 2018 at 11:09 | comment | added | Suvrit | Yes, for a relaxed notion of "solve" you can do this by "learning" -- without making any of those terms precise, there's not much more to say. Most likely what you are looking for in this question is a formulation that can make those terms precise..... | |
| Nov 4, 2018 at 3:23 | answer | added | Mark L. Stone | timeline score: 1 | |
| Nov 3, 2018 at 0:05 | review | First posts | |||
| Nov 3, 2018 at 2:39 | |||||
| Oct 31, 2018 at 20:14 | comment | added | user550103 | No, I am sorry and don't think this is enough. It sounds more numerical approach (which is again iterative method). | |
| Oct 31, 2018 at 20:04 | comment | added | Gerhard Paseman | For the given example, I think one can use "theory" and "experience" to posit a solution vector and a means of finding it. However, I would not want to replace real intuition and experimentation with artificial substitutes. For this problem, I would predict x to be a scalar multiple of y which satisfies the constraint system, and then vary each coordinate of x in a way to decrease the distance while maintaining the constraint. Is that predictive enough for you? Gerhard "In Absence Of Closed-Form Solution" Paseman, 2018.10.31. | |
| Oct 31, 2018 at 17:29 | comment | added | user550103 | @GerhardPaseman: Thank you for your reply. I agree that the question was vague. Now, I have proposed an example that can be a starting point. What do you think about such problems? | |
| Oct 31, 2018 at 17:28 | history | edited | user550103 | CC BY-SA 4.0 |
added 760 characters in body
|
| Oct 30, 2018 at 23:30 | review | Close votes | |||
| Nov 16, 2018 at 3:05 | |||||
| Oct 30, 2018 at 21:08 | comment | added | Gerhard Paseman | The question is somewhat vague. A mildly better (but still too broad for this forum) version is "What characterizes those optimization problems for which one can find a quick convergence to (the desired) optimal points?". I think you will have to slice a piece off this and suggest to this forum a specific example or class of examples to consider. Gerhard "Not Ready To Eat Elephant" Paseman, 2018.10.30. | |
| Oct 30, 2018 at 20:49 | history | asked | user550103 | CC BY-SA 4.0 |