Abstract | ||
---|---|---|
The minimum rate needed to accurately approximate a product distribution based on an unnormalized informational divergence is shown to be a mutual information. This result subsumes results of Wyner on common information and Han-Verdú on resolvability. The result also extends to cases where the source distribution is unknown but the entropy is known. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/CWIT.2013.6621596 | CWIT |
Field | DocType | Volume |
Applied mathematics,Computer vision,Mathematical optimization,Product distribution,Divergence,Differential entropy,Mutual information,Artificial intelligence,Total correlation,Mathematics | Journal | abs/1302.0215 |
Citations | PageRank | References |
11 | 0.86 | 3 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jie Hou | 1 | 97 | 4.39 |
Gerhard Kramer | 2 | 445 | 34.21 |