Principal Inertia Components and Applications
arXiv:1704.00820
Abstract
We explore properties and applications of the Principal Inertia Components (PICs) between two discrete random variables and . The PICs lie in the intersection of information and estimation theory, and provide a fine-grained decomposition of the dependence between and . Moreover, the PICs describe which functions of can or cannot be reliably inferred (in terms of MMSE) given an observation of . 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 fundamental limits of perfect privacy.
arXiv commentOverlaps with arXiv:1405.1472 and arXiv:1310.1512
References in corpus (9)
- The information bottleneck method
- Managing your Private and Public Data: Bringing down Inference Attacks against your Privacy
- A New Data Processing Inequality and Its Applications in Distributed Source and Channel Coding
- Distance-based and continuum Fano inequalities with applications to statistical estimation
- Linear Bounds between Contraction Coefficients for -Divergences
- Remarks on the Most Informative Function Conjecture at fixed mean
- Brascamp-Lieb Inequality and Its Reverse: An Information Theoretic View
- The "Most informative boolean function" conjecture holds for high noise
- Lists that are smaller than their parts: A coding approach to tunable secrecy