Abstract
We analyse Gallager codes by employing a simple mean-field approximation that distorts the model geometry and preserves important interactions between sites. The method naturally recovers the probability propagation decoding algorithm as a minimization of a proper free-energy. We find a thermodynamical phase transition that coincides with information theoretical upper-bounds and explain the practical code performance in terms of the free-energy landscape.
| Original language | English |
|---|---|
| Title of host publication | Advances in neural information processing systems |
| Editors | Todd K. Leen, Volker Tresp, Thomas G. Dietterich |
| Publisher | MIT |
| Pages | 322-328 |
| Number of pages | 7 |
| Volume | 13 |
| ISBN (Print) | 0-2621-2241-3, 978-0-2621-2241-2 |
| Publication status | Published - Apr 2001 |
| Event | 14th Annual Neural Information Processing Systems Conference - Denver, CO, United States Duration: 27 Nov 2000 → 2 Dec 2000 |
Conference
| Conference | 14th Annual Neural Information Processing Systems Conference |
|---|---|
| Abbreviated title | NIPS 2000 |
| Country/Territory | United States |
| City | Denver, CO |
| Period | 27/11/00 → 2/12/00 |