SIsiddhartb_·Sep 22, 2020Submission
Show HN: ExGAN-Adversarial Generation of Extreme Samples
54 points · Open discussionStream-AD
ExGAN
Python2020–2020
Stream-AD / ExGAN
ExGAN
Adversarial Generation of Extreme Samples
2Distinct people
2Mentions
0Explicit recommenders
81GitHub stars
What to know before exploring
What it is
Adversarial Generation of Extreme Samples
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by hour2 dated mentions
Observed mentions: 2020-09-22 10:59:04 UTC to 2020-09-22 14:11:48 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Sep 22, 10:00 | 2020-09-22 10:00:00 UTC | 2020-09-22 11:00:00 UTC | 1 | 0 | 1 |
| Sep 22, 11:00 | 2020-09-22 11:00:00 UTC | 2020-09-22 12:00:00 UTC | 0 | 0 | 0 |
| Sep 22, 12:00 | 2020-09-22 12:00:00 UTC | 2020-09-22 13:00:00 UTC | 0 | 0 | 0 |
| Sep 22, 13:00 | 2020-09-22 13:00:00 UTC | 2020-09-22 14:00:00 UTC | 0 | 0 | 0 |
| Sep 22, 14:00 | 2020-09-22 14:00:00 UTC | 2020-09-22 15:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
2 sourcesExisting GAN based approaches excel at generating realistic samples, but seek to generate typical samples, rather than extreme samples. We propose ExGAN to generate realistic and extreme samples.
ExGAN allows the user to specify both the desired extremeness measure, as well as the desired extremeness probability they wish to sample at. Generating increasingly extreme examples can be done in constant time (with respect to the extremeness probability), as opposed to the exponential time required by the baseline.
Github Repository: https://github.com/Stream-AD/ExGAN
In Show HN: Adversarial Generation of Extreme Samples