Please use this identifier to cite or link to this item:
https://open.uns.ac.rs/handle/123456789/5936
Title: | On the entropy of couplings | Authors: | Kovačević, Marko Stanojević, Ivan Šenk, Vojin |
Issue Date: | 13-Nov-2015 | Journal: | Information and Computation | Abstract: | © 2015 Elsevier Inc. All rights reserved. In this paper, some general properties of Shannon information measures are investigated over sets of probability distributions with restricted marginals. Certain optimization problems associated with these functionals are shown to be NP-hard, and their special cases are found to be essentially information-theoretic restatements of well-known computational problems, such as the Subset sum and the 3-Partition. The notion of minimum entropy coupling is introduced and its relevance is demonstrated in information-theoretic, computational, and statistical contexts. Finally, a family of pseudometrics (on the space of discrete probability distributions) defined by these couplings is studied, in particular their relation to the total variation distance, and a new characterization of the conditional entropy is given. | URI: | https://open.uns.ac.rs/handle/123456789/5936 | ISSN: | 8905401 | DOI: | 10.1016/j.ic.2015.04.003 |
Appears in Collections: | FTN Publikacije/Publications |
Show full item record
SCOPUSTM
Citations
21
checked on May 10, 2024
Page view(s)
11
Last Week
2
2
Last month
0
0
checked on May 10, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.