Timeline for $\epsilon$-net for the set of distributions
Current License: CC BY-SA 4.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 13, 2022 at 8:11 | history | edited | Artur Riazanov | CC BY-SA 4.0 |
added 78 characters in body
|
| Jun 13, 2022 at 8:09 | comment | added | Artur Riazanov | @IosifPinelis, yeah, let me fix that, thank you! | |
| Jun 12, 2022 at 19:53 | comment | added | Iosif Pinelis | I think your $o(1)$ should be specified. Indeed, if $\epsilon>1-1/n$, then the singleton set of the uniform distribution on $X$ is an $\epsilon$-net for $S$. | |
| Jun 12, 2022 at 17:09 | comment | added | Artur Riazanov | @IosifPinelis of size $n^{\omega(1)}$, but preferably I would like to show that the smallest possible $\epsilon$-net for $|X|=n$ has size $c^n$ for some $c > 1$. | |
| Jun 12, 2022 at 16:28 | comment | added | Iosif Pinelis | What do you mean by "super polynomial"? | |
| Jun 12, 2022 at 16:12 | history | edited | Nawaf Bou-Rabee | CC BY-SA 4.0 |
added "total variation"
|
| Jun 12, 2022 at 15:54 | history | asked | Artur Riazanov | CC BY-SA 4.0 |