Calmon, Flavio P. and Makhdoumi, Ali and Medard, Muriel and Varia, Mayank and Christiansen, Mark M. and Duffy, Ken R. (2017) Principal Inertia Components and Applications. IEEE Transactions on Information Theory, 63 (8). pp. 5011-5038. ISSN 1557-9654

Preview

Download (870kB) | Preview

Abstract

We explore properties and applications of the principal inertia components (PICs) between two discrete random variables X and Y. The PICs lie in the intersection of information and estimation theory, and provide a fine-grained decomposition of the dependence between X and Y. Moreover, the PICs describe which functions of X can or cannot be reliably inferred (in terms of MMSE), given an observation of Y. We demonstrate that the PICs play an important role in information theory, and they can be used to characterize information-theoretic limits of certain estimation problems. In privacy settings, we prove that the PICs are related to the fundamental limits of perfect privacy

Item Type:	Article
Additional Information:	This is the preprint version (arXiv:1704.00820) of the published article, which is available at DOI: 10.1109/TIT.2017.2700857
Keywords:	Principal inertia components; estimation; privacy; minimum mean square error;
Academic Unit:	Faculty of Science and Engineering > Research Institutes > Hamilton Institute
Item ID:	10168
Identification Number:	https://doi.org/10.1109/TIT.2017.2700857
Depositing User:	Dr Ken Duffy
Date Deposited:	02 Nov 2018 14:57
Journal or Publication Title:	IEEE Transactions on Information Theory
Publisher:	IEEE
Refereed:	Yes
URI:	https://ieeexplore.ieee.org
Use Licence:	This item is available under a Creative Commons Attribution Non Commercial Share Alike Licence (CC BY-NC-SA). Details of this licence are available here

Repository Staff Only(login required)

Item control page

Downloads

Origin of downloads