Code for ICML2020 paper - CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information
active 2023-08-17 → 2025-12-21 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 858 days from 2023-08-17 to 2025-12-21. Pushes: 1 total, peak 1 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 7 total, peak 1 in a day. Comments: 15 total, peak 3 in a day. Stars: 63 total, peak 3 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| Linear95 | 8 | 1 | 0 | 6 |
| LindgeW | 4 | 0 | 0 | 4 |
| Longdvt | 2 | 0 | 0 | 1 |
| Fred-Tang02 | 2 | 0 | 0 | 0 |
| a2108870 | 1 | 0 | 0 | 0 |
| liutaocode | 1 | 0 | 0 | 1 |
| zhanglonghao1992 | 1 | 0 | 0 | 1 |
| Sannndy0000 | 1 | 0 | 0 | 0 |
| trailblazer-bit | 1 | 0 | 0 | 1 |
| JingHuaMan | 1 | 0 | 0 | 1 |
| liuxiaozhen123 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#28liuxiaozhen1232025-12-19 04:23MI loss
- Issue comment#28Linear952025-12-17 15:38MI loss
- Issue#27Sannndy00002024-08-13 06:39log likelihood becomes nan after some steps
- Issue comment#22JingHuaMan2024-05-18 09:53关于两个tensor的互信息
- Issue comment#6Linear952024-05-10 03:05code requests
- Issue comment#6zhanglonghao19922024-05-10 02:33code requests
- Issue comment#12LindgeW2024-04-11 05:58About the logvar prediction
- Issue comment#12LindgeW2024-04-09 06:57About the logvar prediction
- Issue comment#9LindgeW2024-04-09 06:06The reliability of this method.
- Issue comment#5LindgeW2024-04-09 03:35can I use it for pytorch loss function?
- Issue comment#26Linear952024-03-22 06:21The loss training log-likelihood when (x, y) is absolutely independent
- Issue comment#26Longdvt2024-03-21 06:07The loss training log-likelihood when (x, y) is absolutely independent
- Issue comment#26Linear952024-03-19 04:21The loss training log-likelihood when (x, y) is absolutely independent
- Issue#26Longdvt2024-03-19 01:02The loss training log-likelihood when (x, y) is absolutely independent
- Issue comment#25Linear952024-03-18 06:08Negative Mutual Information Values in Feature Decoupling with MI Minimization
- Issue#25a21088702024-03-16 08:52Negative Mutual Information Values in Feature Decoupling with MI Minimization
- Issue comment#24Linear952023-12-27 07:00Questions about the bound
- Issue#24Linear952023-12-27 06:34Questions about the bound
- Issue comment#24liutaocode2023-12-26 14:46Questions about the bound
- Issue comment#24trailblazer-bit2023-11-18 05:03Questions about the bound
- Issue#24Fred-Tang022023-09-03 03:14Questions about the bound
- Issue#24Fred-Tang022023-09-01 09:20Questions about the bound
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 63 stars here means stars gained during the window, not the repo's star count.