Timeline for Why are Convex Loss Functions important in SGD? [duplicate]
Current License: CC BY-SA 4.0
16 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 18, 2022 at 3:39 | comment | added | Sycorax♦ | I've added another duplicate thread which appears to be a better match for what you're after, in light of the edits & comments. | |
| Feb 18, 2022 at 3:39 | history | duplicates list edited | Sycorax♦ | duplicates list edited from Neural networks: how can convex optimization produce different weights each time? to Neural networks: how can convex optimization produce different weights each time?, When will gradient descent converge to a critical point or to a local/global minima) for non-convex functions? | |
| Feb 18, 2022 at 3:35 | comment | added | CCZ23 | I thought SGD does not work with non-convex losses, right? Or if not, the results are very very poor. If so, why? | |
| Feb 18, 2022 at 3:33 | history | edited | CCZ23 | CC BY-SA 4.0 |
added 397 characters in body
|
| Feb 18, 2022 at 3:33 | comment | added | Sycorax♦ | "Require" for what? | |
| Feb 18, 2022 at 3:33 | comment | added | CCZ23 | The post is somewhat helpful, I still want to know why SGD requires convex functions though when they are not even convex in a NN. This post implies that convex functions are useful because the Hessian is less likely to be positive semi-definite, is this right? I edited my post for this. | |
| Feb 18, 2022 at 3:31 | history | edited | CCZ23 | CC BY-SA 4.0 |
added 397 characters in body
|
| Feb 18, 2022 at 3:26 | comment | added | Sycorax♦ | I think you're asking why a NN is non-convex even if it has a convex loss function, but that's meeting you more than half-way. If the duplicate thread isn't what you're asking about, then you'll need to edit to clarify -- the question reads as if you were reading a specific article and you want to ask about a specific paragraph, but you haven't shared that information in the question. | |
| Feb 18, 2022 at 3:21 | history | closed | Sycorax♦ machine-learning Users with the machine-learning badge or a synonym can single-handedly close machine-learning questions as duplicates and reopen them as needed. | Duplicate of Neural networks: how can convex optimization produce different weights each time? | |
| Feb 18, 2022 at 3:21 | history | reopened | Sycorax♦ | ||
| Feb 18, 2022 at 3:13 | review | Reopen votes | |||
| Mar 20, 2022 at 3:17 | |||||
| Feb 18, 2022 at 3:12 | comment | added | CCZ23 | Does it make sense now @Sycorax? | |
| Feb 18, 2022 at 3:12 | history | edited | CCZ23 | CC BY-SA 4.0 |
added 173 characters in body
Added to review
|
| Feb 18, 2022 at 3:02 | comment | added | Sycorax♦ | It's hard to understand what problem you're trying to solve or you want to learn. Can you edit to clarify what you're doing and how optimization of convex functions fits into solving it? What does it mean for a function to be pointless? | |
| Feb 18, 2022 at 3:01 | history | closed | Sycorax♦ | Needs details or clarity | |
| Feb 18, 2022 at 2:56 | history | asked | CCZ23 | CC BY-SA 4.0 |