Timeline for Applications of 1st order oracle in stochastic convex optimization
Current License: CC BY-SA 4.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 10, 2021 at 16:24 | comment | added | Manuel Madeira | @NawafBou-Rabee thank you for those examples (and sorry for the late reply)! | |
| Apr 26, 2021 at 20:06 | history | edited | Rodrigo de Azevedo | CC BY-SA 4.0 |
added 8 characters in body
|
| Apr 26, 2021 at 14:41 | comment | added | Noah Schweber | Crossposted at MSE: math.stackexchange.com/questions/4117100/… | |
| Apr 26, 2021 at 14:40 | comment | added | Nawaf Bou-Rabee | Also, variational inference arxiv.org/abs/2009.00666 en.wikipedia.org/wiki/Variational_Bayesian_methods | |
| Apr 26, 2021 at 14:32 | history | edited | Manuel Madeira | CC BY-SA 4.0 |
deleted 5 characters in body
|
| Apr 26, 2021 at 14:23 | comment | added | Nawaf Bou-Rabee | Do you mean something like arxiv.org/abs/1412.4845 ? In the linked file on adaptive importance sampling, the authors apply stochastic optimization to an expectation that is not a finite-sum. | |
| Apr 26, 2021 at 14:19 | comment | added | Manuel Madeira | @Dirk, I edited the question and hope that it is clearer now. I want to know the applications of a more general setting but that includes the finite-sum setting. Thank you for your feedback | |
| Apr 26, 2021 at 14:17 | history | edited | Manuel Madeira | CC BY-SA 4.0 |
added 258 characters in body
|
| Apr 26, 2021 at 11:02 | comment | added | Dirk | Sorry, but I don't get what you ask. In the finite sum example one has $f(x) = \tfrac1n\sum_{i=1}^n f_i(x)$ and then $\nabla f_i(x)$ is a "noisy version" of $\nabla f(x)$, it is even an unbiased estimator in the sense that the expected value of $\nabla f_i(x)$ (if you choose i uniformly) is $\nabla f(x)$. Is this related to your question? | |
| Apr 26, 2021 at 9:53 | history | asked | Manuel Madeira | CC BY-SA 4.0 |